ISY503 Intelligent Systems

ISY503_Assessment_3_Brief_Final Project_Module 12 Page 1 of 9
Task Summary
In a group (approximately 3 or 4) you should apply the foundational principles of AI to a Natural Language Processing (NLP) or Computer Vision project capable of solving a specific problem. There are two problems defined for this task – and you will need to choose one. The NLP based task is where you can implement a sentiment analysis project. The Computer Vision project will provide you an opportunity to train a model based on sample data that will let you perform a a self-driving simulation without crashing or leaving the road.
If you choose the NLP-based task, your solution should be delivered as a simple website with a text box to enter a sample statement for sentiment analysis and a button to execute the sentiment analysis function. The interface should also present the outcome of executing the sentiment analysis function on the page. Note that you will be training a machine learning model to analyse the sentiments of customers reviews and creating a prediction function to allow for the input text to be subject to sentiment analysis based on your trained model.
ASSESSMENT 3 BRIEF
Subject Code and Title
ISY503 Intelligent Systems
Assessment
Final Project
Individual/Group
Group & Individual
Length
Presentation, Code and Individual contribution report
Volume of assessment: Presentation 10-15 minutes total (group), Individual report (250 words +/- 10%)
Learning Outcomes
The Subject Learning Outcomes demonstrated by successful completion of the task below include:
a) Determine suitable approaches towards the construction of AI systems.
b) Determine ethical challenges which are distinctive to AI and issues that may arise with such rapidly developing technologies.
c) Apply knowledge based or learning based methods to solve problems in complex environments that attempt to simulate human thought and decision making processes, allowing modern society to make further advancements.
d) Communicate clearly and effectively using the technical language of the field and constructively engage with different stakeholders.
e) Apply the foundational principles of AI learnt throughout the course and apply it to the different areas of Natural Language Processing, Speech Recognition, Computer Vision and Machine Learning.
Submission
Due by 11:55pm AEST Sunday end of Module 12 (Week 12).
Weighting
40%
Total Marks
100 marks
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 2 of 9
With the Computer Vision project, there is also a need to train a model that the simulator will use to run a simulation based on sample data. The model (which is trained on this sample data) will need to be submitted as a deliverable along with a video of a full lap of the car doing a lap in the simulator.
Context
This assessment moves further into solving a more realistic program by building a more complex Intelligent System. The Intelligent System can either be an application in Natural Language Processing or Computer Vision – two of the key focus areas in industry and academia.
The project will also give you an opportunity to hone your skills and be able to collaborate with other individuals in a team. Collaboration is common in the workplace, and therefore a skill worth practising. The group work in this assessment will help you to identify the skills you might need to refine and help you to understand how to communicate better with your team mates. There is also a presentation and report deliverable that will help you practise your verbal and written communication skills as these will prove to be vital in the workplace.
Task Instructions
You should work in a group of 3 or 4 people (depending on the numbers in your class) and the tasks of each person should be determined at the beginning of your project. This is important to ensure expectations of individual contributions are set. You are required to use the version control tools Git that can also keep a track of collaboration between members. You also need to deliver a presentation that should be no longer than 15 minutes, and is based on the project you have implemented together. Individually, you must also prepare a report explaining each team member’s contribution to the project (250 words). The individual report explains the contribution each person made to the assessment task. Finally, you should include a self-assessment of your perceived percentage contribution to the overall assessment task, and how much each team member contributed. Further instructions and detail are provided below.
To complete this assessment task you must:
• Participate in a group project to develop an NLP or a Computer Vision project. Your project can either be the NLP or the Computer Vision application.
o In case of the NLP, you need to use the following link to the dataset http://www.cs.jhu.edu/~mdredze/datasets/sentiment/index2.html The dataset is a collection of Amazon product reviews across several categories. Your task will be to train a neural network to perform sentiment analysis to allow it to match with one of the categories in the dataset. Note that the dataset already contains labelled data for positive and negative reviews. You should load all the negative and positive comments, mix and randomise the data, take some percentage of data to train your model, and use the rest for testing your model. Your solution needs to be able to:
 Clean the data (punctuation, spelling etc.)
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 3 of 9
 Encode the words in the review
 Encode the labels for ‘positive’ and ‘negative’
 Conduct outlier removal to eliminate really short or wrong reviews.
 Pad/truncate remaining data
 Split the data into training, validation and test sets
 Obtain batches of training data (you may use DataLoaders or generator functions)
 Define the network architecture
 Define the model class
 Instantiate the network
 Train your model
 Test
 Develop a simple web page/create an executable of your solution that will take an input sentence and provide an output of whether the review sentiment was positive or negative.
 Run an inference on some test input data – both positive and negative and observe how often the model gets these right.
 Repeat training and rearchitect the model if required.
o Keep in mind your ethical responsibility as a data science practitioner of the need to be fair and uniform in deriving accurate sentiment from a product review when conducting the above i.e. the dataset may have been split into positive and negative by the owner, however, can you identify any issues in their decision that you’ve now addressed? Note these in your report.
o Deploy the system on a simple website or provide an executable which can be run on the command line.
o The interface for the NLP solution should have an input field to insert an input sentence into as well as a button to execute the sentiment analysis function you’ve implemented. Note that the facilitator will test out a few input statements to verify the accuracy of your model’s sentiment analysis capability. The execution of the sentiment analysis should produce an output once an input sentence is entered into the field and the button clicked in the form of “Positive review” or “Negative review” as a text output. If you’re confident that you’ve trained your model sufficiently well on the training data, experiment to see what results you get when you provide it a sample input that is outside the training data.
o IF you choose to work on the Computer Vision project, you will work on Udacity’s self-driving car simulator project. The download link to the simulator is provided below as is the training data. Your task is to build a machine learning model that is trained on the data provided and when run on the simulator, will hopefully keep the car on the road without running off track. You can download the Simulator here: https://github.com/udacity/self-driving-car-sim. Follow the instructions on this page to install the game and its requisite frameworks.
o You will then use the images in the Assessment 3 folder in Blackboard to train your model.
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 4 of 9
 You will find three folders (Left, Right, and Forward) when you unzip the file. Use these images to train your model.
o . This project will require you to submit your code files on GitHub including the following:
 model.py (script used to create and train the model)
 drive.py (script to drive the car – feel free to modify this file)
 model.h5 (a trained Keras model)
 video.mp4 (a video recording of your vehicle driving autonomously around the track for at least one full lap)
o You may consult the website https://medium.com/activating-robotic-minds/introduction-to-udacity-self-driving-car-simulator-4d78198d301d for assistance on how to work with the simulator. This file is also in your Assessment 3 folder in Blackboard.
o Keep in mind your responsibilities as a data science practitioner and consider the ethical considerations of an application as a self-driving car. For instance, the need to consider the various factors on the road when a machine is in charge of navigating the vehicle.
o Use version control tools and pair programming through Git for either project. The project should be submitted to Github and the link to Github should be provided in the report.
• Participate in a group presentation of your work (this means each of you must present for a few minutes). The presentation should address rationale behind the choice of project, any ethical considerations made during implementation, the accuracy of the outputs observed, and a brief explanation of implementation. The presentation delivery should be split among the team members. It is up to the group to determine who submits the final video presentation (in Blackboard). You may want to have an online group meeting (zoom/skype etc) where you record yourselves presenting (sharing your screen with the ppt as the primary view, and each of you present your section verbally over the top).
• Write a short individual report (250 words) specifying your contribution to the work and the perceived contribution of the other members of your group. The total of your percentages should add to 100% (e.g., Tom: 15%, Rajiv 25%, Esfir 30%, Jasmine 30%).
o The manual should list any ethical considerations about NLP or Computer Vision based on your selected project cited with APA referencing.
Referencing
It is essential that you use appropriate APA style for citing and referencing research. Please see more information on referencing here http://library.laureate.net.au/research_skills/referencing
Submission Instructions
There are three elements that need to be completed for Assessment 3:
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 5 of 9
1) Group Code (only one member of the group needs to submit this)
2) Group video Presentation (only one member of the group needs to submit the final version of this)
3) Individual report and contribution summary, this includes a list of your team members with student ID’s (each team member must submit this individually)
Submit this task via the Assessment 3 link in the main navigation menu in ISY503: Intelligent Systems. If you have any questions or concerns please get in touch with your learning facilitator early, do not leave this until the last minute. The Learning Facilitator will provide feedback via the Grade Centre in the LMS portal. Feedback can be viewed in My Grades.
Academic Integrity Declaration
Individual assessment tasks:
I declare that except where I have referenced, the work I am submitting for this assessment task is my own work. I have read and am aware of Torrens University Australia Academic Integrity Policy and Procedure viewable online at http://www.torrens.edu.au/policies-and-forms
I am aware that I need to keep a copy of all submitted material and their drafts, and I will do so accordingly.
Group assessment tasks:
We declare that except where we have referenced, the work we are submitting for this assessment task is our own work. We have read and are aware of Torrens University Australia Academic Integrity Policy and Procedure viewable online at http://www.torrens.edu.au/policies-and-forms
We are aware that we need to keep a copy of all submitted material and their drafts, and we will do so accordingly.
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 6 of 9
Assessment Rubric
Assessment Attributes
Fail
(Yet to achieve minimum standard)
0-49%
Pass (Functional)
50-64%
Credit (Proficient)
65-74%
Distinction (Advanced)
75-84%
High Distinction (Exceptional)
85-100%
Project correctness
The project has determined a suitable approach towards the construction of AI systems, including any ethical considerations that are relevant
Percentage for this criterion = 40%
Project has not been implemented or delivered or has been copied from external source without any modifications (the source of NLP or Computer Vision project should be mentioned in the manual report).
Ethical considerations are not considered.
The NLP or Computer Vision project has been modified a little not showing enough contribution from students (the contributed parts should be highlighted with comments and the main source should also be mentioned in the manual report).
Ethical considerations are mentioned without addressing the potential concerns.
The NLP or Computer Vision project has been implemented in such a way that shows sufficient contribution of students to it. In other words, it is not just copied from another source (the contributed parts should be highlighted with comments and the main source should also be mentioned in the manual report).
If the NLP project has been implemented, it allows for inputs through a text box on a web interface or through a command line executable. When a sample positive or negative input statement is provided (from the training data), it provides the right right sentiment classification 80% of the time.
In case of Computer Vision solution, the model has
The NLP or Computer Vision project has been implemented in such a way that shows sufficient contribution of students to it. In other words, it is not just copied from another source (the contributed parts should be highlighted with comments and the main source should also be mentioned in the manual report).
If the NLP project has been implemented, it allows for inputs through a text box on a web interface or through a command line executable. When a sample positive or negative input statement is provided (from the training data), it accurately (>90% but less than 100% of the time) provides the right sentiment classification. .
In case of Computer Vision solution, the model has
The NLP or Computer Vision project has been implemented in such a way that shows sufficient contribution of students to it. In other words, it is not just copied from another source (the contributed parts should be highlighted with comments and the main source should also be mentioned in the manual report).
If the NLP project has been implemented, it allows for inputs through a text box on a web interface or through a command line executable. When a sample positive or negative input statement is provided (not necessarily from the training data), it accurately (100% of the time) provides the right sentiment classification.
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 7 of 9
Assessment Attributes
Fail
(Yet to achieve minimum standard)
0-49%
Pass (Functional)
50-64%
Credit (Proficient)
65-74%
Distinction (Advanced)
75-84%
High Distinction (Exceptional)
85-100%
been trained on the provided training data and successfully completes a lap on the road with some deviations.
Ethical considerations are identified and discussed.
been trained on the provided training data and successfully completes a lap on the road with only a few minor deviations.
Ethical considerations are highlighted and addressed in detail.
In case of Computer Vision solution, the model has been trained on the provided training data and successfully completes a lap on the road with no deviations.
Ethical considerations are highlighted and comprehensively addressed
Effective Communication (Presentation/Oral)
Evidence of clear communication and effective use of the technical language of the field
Percentage for this criterion = 30%
Difficult to understand for audience, no logical/clear structure, poor flow of ideas, argument lacks supporting evidence.
Specialised language and terminology is rarely or inaccurately employed.
Stilted, awkward and/or oversimplified delivery.
Limited use of engaging presentation techniques.
Presentation is sometimes difficult to follow.
Information, arguments and evidence are presented in a way that is not always clear and logical.
Employs some specialised language and terminology with accuracy.
Correct, but often stilted or awkward delivery.
Sometimes uses engaging presentation techniques (e.g.
Presentation is easy to follow.
Information, arguments and evidence are well presented, mostly clear flow of ideas and arguments.
Accurately employs specialised language and terminology.
Correct, but occasionally stilted or awkward delivery.
Uses engaging presentation techniques (e.g. posture;
Engages audience interest.
Information, arguments and evidence are very well presented; the presentation is logical, clear and well-supported by evidence.
Accurately employs a wide range of specialised language and terminology.
Clear and confident delivery.
Confidently and consistently uses a range of engaging
Engages and sustains audience interest.
Expertly presented; the presentation is logical, persuasive, and well- supported by evidence, demonstrating a clear flow of ideas and arguments.
Discerningly selects and precisely employs a wide range of specialised language and terminology.
Clear, confident and persuasive delivery.
Dynamic, integrated and professional use of a wide
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 8 of 9
Assessment Attributes
Fail
(Yet to achieve minimum standard)
0-49%
Pass (Functional)
50-64%
Credit (Proficient)
65-74%
Distinction (Advanced)
75-84%
High Distinction (Exceptional)
85-100%
(e.g. posture; eye contact; gestures; volume, pitch and pace of voice)
Presentation aids are not employed or developed as directed.
No reference is made to the following within the presentation content:
the rationale behind the choice of project, any ethical considerations made during implementation, the accuracy of the outputs observed, and a brief explanation of implementation
posture; eye contact; gestures; volume, pitch and pace of voice)
Employs basic, but generally accurate presentation aids as directed. A number of aspects require further refinement (e.g. amount of information, styling, editing, etc.).
The content of the presentation mentions some of the following: the rationale behind the choice of project, any ethical considerations made during implementation, the accuracy of the outputs observed, and a brief explanation of implementation
eye contact; gestures; volume, pitch and pace of voice)
Employs clear and somewhat engaging presentation aids as directed. A few aspects require further refinement (e.g. amount of information, styling, editing, etc.)
The content of the presentation briefly touches on each of: the rationale behind the choice of project, any ethical considerations made during implementation, the accuracy of the outputs observed, and a brief explanation of implementation
presentation techniques (e.g. posture; eye contact, expression; gestures; volume, pitch and pace of voice; stance; movement)
Employs succinct, styled and engaging presentation aids that incorporate a range of elements (graphics, multi-media, text, charts, etc.).
The content of the presentation addresses in some detail: the rationale behind the choice of project, any ethical considerations made during implementation, the accuracy of the outputs observed, and a brief explanation of implementation
range of engaging presentation techniques (e.g. posture; eye contact, expression; gestures; volume, pitch and pace of voice; stance; movement)
Employs succinct, creative and engaging presentation aids that effectively integrate a wide range of elements (graphics, multi-media, text, charts, etc.).
The content of the presentation addresses in great detail: the rationale behind the choice of project, any ethical considerations made during implementation, the accuracy of the outputs observed, and a brief explanation of implementation
Individual contribution
No evidence of individual contribution.
A report with self-assessment and team members’ assessment has been provided
A report with self-assessment and team members’ assessment has been provided
A report with self-assessment and team members’ assessment has been provided.
A manual with self-assessment and team members’ assessment has been provided.
ISY503_Assessment_3_Brief_Final Project_Module 12 Page 9 of 9
Assessment Attributes
Fail
(Yet to achieve minimum standard)
0-49%
Pass (Functional)
50-64%
Credit (Proficient)
65-74%
Distinction (Advanced)
75-84%
High Distinction (Exceptional)
85-100%
Percentage for this criterion = 30%
No report with self-assessment and team members assessment has been provided
Basic attempt at describing individual contribution in the report and group code.
No ethical considerations of NLP or Computer Vision based on the selected project has been listed in the report.
The report and group code demonstrates a structure of contribution from team members with individual contribution briefly discussed.
The report lists at least one reasonable ethical aspect of the chosen project.
The report and group code demonstrates a considered effort in establishing a structure of contribution from team members with individual contributions discussed in detail.
The report lists multiple reasonable ethical aspects of the chosen project.
The report demonstrates significant thought being given to establishing a structure of contribution from team members with individual contributions of the student to the project explained in detail.
The report lists multiple reasonable ethical aspects and their implications on on the chosen project.
The following Subject Learning Outcomes are addressed in this assessment
SLO a)
Determine suitable approaches towards the construction of AI systems.
SLO b)
Determine ethical challenges which are distinctive to AI and issues that may arise with such rapidly developing technologies.
SLO c)
Apply knowledge based or learning based methods to solve problems in complex environments that attempt to simulate human thought and decision making processes, allowing modern society to make further advancements.
SLO d)
Communicate clearly and effectively using the technical language of the field and constructively engage with different stakeholders.
SLO e)
Apply the foundational principles of AI learnt throughout the course and apply it to the different areas of Natural Language Processing, Speech Recognition, Computer Vision and Machine Learning.

Case Study Report

ISY503_Assessment_1_Brief_Case Study_Module 5Page 1 of 6
ASSESSMENT 1 BRIEF
Subject Code and Title ISY503 Intelligent Systems
Assessment Case Study Report
Individual/Group Individual
Length 1500 words (+/- 10%)
Learning Outcomes The Subject Learning Outcomes demonstrated by successful
completion of the task below include:
a) Determine suitable approaches towards the construction of
AI systems.
b) Determine ethical challenges which are distinctive to AI and
issues that may arise with such rapidly developing
technologies.
d) Communicate clearly and effectively using the technical
language of the field and constructively engage with
different stakeholders.
Submission Due by 11:55pm AEST Sunday end of Module 5 (Week 5).
Weighting 25%
Total Marks 100 marks
Task Summary
You are to write a report based on a case study that focusses on the application of an intelligent
system. Intelligent systems can encompass many AI centred systems but the main focus of this
assessment is Computer Vision and Natural Language Processing (NLP).
Computer vision, as a field, is progressing at a rapid rate helped in part by advances in deep learning.
There are many challenges in computer vision including; dual priorities, speed for real-time detection,
limited data, class imbalance, and ethics. There are many Computer Vision problems including object
detection, gesture recognition, hand sign detection, satellite image classification, to name just a few.
NLP has given us the ability to talk to a machine (voice as input), such as the AI-based systems like
Alexa or Siri, and be understood. Alas there is still a long way to go before we have systems that exhibit
a real understanding of natural language (Natural Language Understanding/NLU), as ultimately
computers need to be able to determine polarization and sentiment analysis, emotion analysis, topic
detection and classification.
For this assessment you will be provided with a choice between a computer vision case study, and a
natural language processing case study. Select one case study only. Your facilitator will give you the
case studies during Module 1 (Week 1).
The report should be 1500 words (+/- 10%) and is an individual piece of work.
ISY503_Assessment_1_Brief_Case Study_Module 5Page 2 of 6
Context
Exploring various applications of intelligent systems will give you a greater understanding of the use
and efficacy of these systems, to solve simple through to complex problems. Learning to analyse the
suitability of different AI methods, the ethical issues associated with them, and the technical language
used in the industry is essential to ensure you are able to articulate the challenges around
implementation of the intelligent system being discussed. Using case studies that focus on intelligent
systems will bolster your analytical skills, helping you to think through the how, why, when and where
of implementing such a system. By completing this assessment you will to appreciate the real-life
application of intelligent systems, and begin to identify opportunities to utilise these systems across a
breadth of problems.
Task Instructions
To complete this assessment task you must write a case study report with the following sections:
 Introduction: This section should introduce the case study you have been given, and
highlight the significance of the problem it seeks to address.
 Background: This section should provide sufficient background information on, and explain
the application of, the intelligent system including machine learning models and methods.
 Method: Elaborate here on the method(s) used and explain how the research was
undertaken. You should include the source of data used in the case study, and identify any
ethical issues that may have arisen upon its use (e.g., medical history of patients).
 Results: What was the outcome of the case study?
 Discussion: In this section you should explain the relevant and significance of your chosen
study, and you should identify obstacles restricting the intelligent system. You should also
mention any constraints reported in the article.
 Recommendations: This section should include critical perspectives and recommendations
to improve or enhance the system.
 References: You should support your report with additional peer-reviewed journal articles.
These should be in appropriate APA style.
Referencing
It is essential that you use appropriate APA style for citing and referencing research. Please see more
information on referencing here http://library.laureate.net.au/research_skills/referencing
Submission Instructions
Submit your 1500 word case study report task via the Assessment 1 link in the main navigation
menu in ISY503: Intelligent Systems. Please ensure your student ID and assessment number are
contained in the file name, e.g., 904581t_ISY503_Assessment 1. The Learning Facilitator will provide
feedback via the Grade Centre in the LMS portal. Feedback can be viewed in My Grades.
ISY503_Assessment_1_Brief_Case Study_Module 5Page 3 of 6
Academic Integrity Declaration
I declare that except where I have referenced, the work I am submitting for this assessment task is
my own work. I have read and am aware of Torrens University Australia Academic Integrity Policy
and Procedure viewable online at http://www.torrens.edu.au/policies-and-forms
I am aware that I need to keep a copy of all submitted material and their drafts, and I will do so
accordingly.
ISY503_Assessment_1_Brief_Case Study Report_Module 5 Page 4 of 6
Assessment Rubric
Assessment
Attributes
Fail
(Yet to achieve
minimum standard)
0-49%
Pass
(Functional)
50-64%
Credit
(Proficient)
65-74%
Distinction
(Advanced)
75-84%
High Distinction
(Exceptional)
85-100%
Evaluation of
information selected to
support the case study
Percentage for this
criterion = 40%
Limited understanding of
key concepts required to
support the case study.
Confuses logic and
emotion. Information
taken from reliable
sources but without a
coherent analysis or
synthesis.
Viewpoints of experts are
taken as fact with little
questioning.
The implementation of
the system has not been
understood.
Resembles a recall or
summary of key ideas.
Often conflates/confuses
assertion of personal opinion
with information
substantiated by evidence
from the research/course
materials.
Analysis and evaluation do
not reflect expert judgement,
intellectual independence,
rigor and adaptability.
Implementation of the
system has been understood
but not in details for reimplementation.
Supports personal opinion
and information
substantiated by evidence
from the research/course
materials.
Demonstrates a capacity to
explain and apply relevant
concepts.
Identifies logical flaws.
Questions viewpoints of
experts.
Implementation of the
system has been
understood but not in
details for reimplementation.
Discriminates between
assertion of personal
opinion and information
substantiated by robust
evidence from the
research/course materials
and extended reading.
Well demonstrated capacity
to explain and apply
relevant concepts.
Viewpoint of experts are
subject to questioning.
Analysis and evaluation
reflect growing judgement,
intellectual independence,
rigor and adaptability.
Implementation of the
system has been
understood but reimplementing
the system
needs more details in no
more than two parts.
Systematically and critically
discriminates between
assertion of personal
opinion and information
substantiated by robust
evidence from the
research/course materials
and extended reading.
Information is taken from
sources with a high level of
interpretation/evaluation
to develop a
comprehensive critical
analysis or synthesis.
Identifies gaps in
knowledge.
Exhibits intellectual
independence, rigor, good
judgement and
adaptability.
Fully understands how to
re-implement the system
again and also in an
optimised way.
ISY503_Assessment_1_Brief_Case Study Report_Module 5 Page 5 of 6
Assessment
Attributes
Fail
(Yet to achieve
minimum standard)
0-49%
Pass
(Functional)
50-64%
Credit
(Proficient)
65-74%
Distinction
(Advanced)
75-84%
High Distinction
(Exceptional)
85-100%
Ethical Considerations
Ethical issues have been
identified and
considered in the
context of AI and its
rapid development
Percentage for this
criterion = 20%
Data source and ethical
matters associated with it
is not addressed.
Data source and ethical
matter associated with it is
identified but not discussed.
Data sources used in
implementation and ethical
matters associated with it
have been identified and
discussed at a shallow level.
Data sources used in the
case study implementation
and ethical matters
associated with it have
been comprehensively
identified and discussed.
Data sources used in the
case study implementation
and ethical matters
associated with it have
been comprehensively
identified and discussed.
Alternative suggestions
have been made in light of
the issues identified.
Effective
Communication
(Written)
Percentage for this
criterion = 25%
Presents information.
Specialised language and
terminology is rarely or
inaccurately employed.
Meaning is repeatedly
obscured by errors in the
communication of ideas,
including errors in
structure, sequence,
spelling, grammar,
punctuation and/or the
Communicates in a readable
manner that largely adheres
to the given format.
Generally employs specialised
language and terminology
with accuracy.
Meaning is sometimes
difficult to follow.
Information, arguments and
evidence are structured and
sequenced in a way that is
not always clear and logical.
Communicates in a
coherent and readable
manner that adheres to the
given format.
Accurately employs
specialised language and
terminology.
Meaning is easy to follow.
Information, arguments and
evidence are structured and
sequenced in a way that is
clear and logical.
Communicates coherently
and concisely in a manner
that adheres to the given
format.
Accurately employs a wide
range of specialised
language and terminology.
Engages audience interest.
Information, arguments and
evidence are structured and
sequenced in a way that is,
clear and persuasive.
Communicates eloquently.
Expresses meaning
coherently, concisely and
creatively within the given
format.
Discerningly selects and
precisely employs a wide
range of specialised
language and terminology.
Engages and sustains
audience’s interest.
Information, arguments
and evidence are insightful,
persuasive and expertly
presented.
ISY503_Assessment_1_Brief_Case Study Report_Module 5 Page 6 of 6
Assessment
Attributes
Fail
(Yet to achieve
minimum standard)
0-49%
Pass
(Functional)
50-64%
Credit
(Proficient)
65-74%
Distinction
(Advanced)
75-84%
High Distinction
(Exceptional)
85-100%
acknowledgment of
sources.
Some errors are evident in
spelling, grammar and/or
punctuation.
Occasional minor errors
present in spelling,
grammar and/or
punctuation.
Spelling, grammar and
punctuation are free from
errors.
Spelling, grammar and
punctuation are free from
errors.
Correct citation of key
resources and evidence
Percentage for this
criterion = 15%
Demonstrates
inconsistent use of good
quality, credible and
relevant resources to
support and develop
ideas.
Referencing is omitted or
does not resemble APA.
Demonstrates use of credible
and relevant resources to
support and develop ideas,
but these are not always
explicit or well developed.
Referencing resembles APA,
with frequent or repeated
errors.
Demonstrates use of
credible resources to
support and develop ideas.
Referencing resembles APA,
with occasional errors.
Demonstrates use of good
quality, credible and
relevant resources to
support and develop
arguments and statements.
Show evidence of wide
scope within the
organisation for sourcing
evidence.
APA referencing is free
from errors.
Demonstrates use of highquality,
credible and
relevant resources to
support and develop
arguments and position
statements.
Show evidence of wide
scope within and without
the organisation for
sourcing evidence.
APA referencing is free
from errors.
The following Subject Learning Outcomes are addressed in this assessment
SLO a) Determine suitable approaches towards the construction of AI
SLO b) Determine ethical challenges which are distinctive to AI and issues that may arise with such rapidly developing technologies.
SLO d) Communicate clearly and effectively using the technical language of the field and constructively engage with different stakeholders.

Deep Learning Final Project

DLE602_Assessment 3 Brief_Source code & report_Module 12 Page 1 of 7
Task Summary
In Assessment 2, your group reviewed quality research articles in the field of deep learning and proposed a research project for implementation based on the literature review. You also presented your project proposal to wider audience in a 5–7-minute audio-visual seminar.
In Assessment 3, you and your group members will continue to work on the proposed project and will implement the project based on the Deep Learning principles discussed and learned in this subject.
Your group will also produce a professional report detailing the entire implementation process, including a clear list of the requirements/functionalities, the steps taken to address those requirements, the deep learning principles considered for the implementation, the methods used and an analysis of the outcomes.
Please refer to the Task Instructions (below) for further details on how to complete this task.
Context
The aim of this assessment is to gain implementation experience of a deep learning project concerning a real-life issue. The written report should demonstrate your ability to practically implement the theories you learned in the modules.
ASSESSMENT 3 BRIEF
Subject Code and Title
DLE602 Deep Learning
Assessment
Deep Learning Final Project
Individual/Group
Group
Length
1,500 words (+/–10%) Report and Source Code
Learning Outcomes
The Subject Learning Outcomes demonstrated by the successful completion of the task below include:
c) Develop critical analysis skills in deep learning research.
d) Demonstrate collaborative skills to apply deep learning to solve real world problems.
e) Demonstrate ability to effectively communicate scientific and technical information.
Submission
Due by 11:55pm AEST/AEDT Sunday end of Module 12.
Weighting
40%
Total Marks
100 marks
DLE602_Assessment 3 Brief_Source code & report_Module 12 Page 2 of 7
Task Instructions
Your group will implement the project identified in the previous assessment using Python programming language. The code must be well formatted and conform to Python naming conventions. You also need to provide sufficient comments in the code.
You are also required to prepare a 1500-word report in which you will integrate knowledge from your literature review and your Assessment 2 report. You need to highlight all the key points that you considered for implementation and demonstrate what you have undertaken to complete the key points. In the report, you will also discuss the process of implementation and the outcomes.
The report should demonstrate that the group fully understands the deep learning concepts learned in the subject. The report should provide concluding remarks that show the analysis and synthesis of ideas.
It should be noted that this is a new report and not the same as that produced in Assessment 2. In the previous report, you defined the project. In this assessment, your focus should be on the implementation of the project and demonstrating your knowledge of deep learning.
Report Guidelines
In relation to the report, you need to:
• Prepare a 1,500-word report in which you clearly articulate the entire process you adopted to implement your project and your project outcomes;
• Provide a concise summary of the previous assessment, including the project statement, aim and research question(s);
• Present your report using any standard writing format;
• Include a cover page and table of contents. Note: the cover page needs to include official student names and numbers;
• State the word count at the end of the report (before the reference section);
• Insert page numbers (the page numbers should appear in the footer of each page with your group id); and
• Label any figures and tables in your report with meaningful captions.
Referencing
It is essential that you use APA style to cite and reference your research. For more information on referencing, visit our Library website at: https://library.torrens.edu.au/academicskills/apa/tool.
Submission Instructions
Compile your written PDF or word report and your source code with instructions on how to execute the code in a zip file. Ensure that you have the names and student ID of the members of the group on the front page. Submit the zip file using Assessment link in the main navigation menu for ‘DLE602 Deep Learning Assessment 3’.
DLE602_Assessment 3 Brief_Source code & report_Module 12 Page 3 of 7
Academic Integrity Declaration
We declare that except where we have referenced, the work we are submitting for this assessment task is our own work. We have read and are aware of Torrens University Australia Academic Integrity Policy and Procedure viewable online at http://www.torrens.edu.au/policies-and-forms
We are aware that we need to keep a copy of all submitted material and their drafts, and we will do so accordingly.
DLE602_Assessment 3 Brief_Source code & report_Module 12 Page 4 of 7
Assessment Rubric
Assessment Attributes
Fail
(Yet to achieve minimum standard)
0–49%
Pass (Functional)
50–64%
Credit (Proficient)
65–74%
Distinction (Advanced)
75–84%
High Distinction (Exceptional)
85–100%
Completeness and efficiency
• The implementation covers all requirements
• The whole system is easy to use and run
Percentage for this criterion = 20%
None of the requirements have been implemented.
The system does not function properly or is extremely buggy.
An extreme level of manual configuration is required to run the system. Additionally, the configuration does not work.
One or two major requirements have been implemented.
The system does not function properly. No exception handling has been implemented.
Users are required to follow a lengthy configuration manual to run the system.
All but one or two major requirements have been implemented.
The system functions only if certain additional conditions are met. Basic exception handling has been implemented, but it is not thorough.
Users are required to follow a short configuration manual to run the system.
Most of the major requirements have been implemented.
The system functions without any additional conditions needing to be met. Basic exception handling has been implemented, but it is not thorough.
Users are only required to copy the necessary data in the right locations.
All of the major requirements have been implemented.
The system functions properly. Exceptions are handled very well.
Users can run the system without any configuration.
Coding Convention and Quality of Code
• The code follows a consistent naming convention
• The code is well formatted and includes appropriate spacing and indentation
The code is not formatted.
Little or no comments are provided.
The naming of the methods or variables is inconsistent. No naming convention is followed.
There are significant errors in the format of the code and the naming of the methods or variables.
There is a significant lack of useful comments.
The code is generally well written, but there is some room for improvement.
There are more than five errors but less than eight errors in terms of the naming conventions and the format of the code.
The code is generally well written.
There are more than two errors but less than five errors in terms of the naming conventions and the format of the code.
The code is expertly written.
There are no more than two errors in terms of the naming conventions and the format of the code.
DLE602_Assessment 3 Brief_Source code & report_Module 12 Page 5 of 7
• The code contains sufficient comments; the implementation of the major functions are commented upon
Percentage for this criterion = 20%
There is a reasonable amount of useful comments.
There is a sufficient amount of useful comments.
There is a sufficient amount of useful comments.
Integration of Knowledge, Topic Focus, Depth of Discussion
• Clear requirements
• Articulation of deep learning principles and necessary methods
Percentage for this criterion = 30%
The list of requirements/functionalities and project scope are not in sync.
The review of the implementation, deep learning principles and methods does not highlight the relationship between the theories and the implementation.
No analysis of the outcomes is presented.
The list of requirements/functionalities and project scope barely match.
The review of the implementation, deep learning principles and methods barely highlight the relationship between the theories and the implementation.
A short analysis of the outcomes is presented.
The list of requirements/functionalities overfits or underfits the project scope.
The review of the implementation, deep learning principles and methods loosely highlight the relationship between the theories and the implementation.
A high-level analysis of the outcomes is presented.
The list of requirements/functionalities manageable within the project scope is somewhat clear.
The review of the implementation, deep learning principles and methods highlight the relationship between the theories and the implementation.
A critical analysis of the outcomes is presented.
Presents a clear list of the requirements/functionalities manageable within the project scope.
Excellent review of implementation, deep learning principles and methods. A clear relationship between the theories and implementation is established.
A comprehensive and critical analysis of the outcomes is presented.
DLE602_Assessment 3 Brief_Source code & report_Module 12 Page 6 of 7
Effective Communication (Written)
• Writing skills
• Organisation and structure
Percentage for this criterion = 15%
Poor writing skills. Additionally, the articulations are not clear at all.
Lack overall organisation
Very difficult to follow
Grammar and spelling errors make it difficult for the reader to interpret the text in many places.
Writing is readable; however, it is difficult to comprehend the information presented.
Not well organised for the most part.
Difficult to follow.
Choice of words needs to be improved.
Grammatical errors impede the flow of communication.
Writing is readable and it is reasonably easy to comprehend the information presented.
Organised for the most part.
Difficult to follow.
Words are well chosen; however, some minor improvements are needed.
Sentences are mostly grammatically correct and contain few spelling errors.
Writing is good and it is easy to comprehend the information presented.
Well organised.
Cohesive and easy to follow.
Words are well chosen.
Sentences are grammatically correct and free of spelling errors.
Writing is excellent, short, sharp and to-the-point and easily digestible.
Exceptionally organised.
Highly cohesive and easy to follow.
Words are carefully chosen that precisely express the intended meaning and support reader comprehension.
Documentation
• Headings and sub-topics formatting
• Professional presentation
• Referencing
Percentage for this criterion = 15%
Headings are used and not numbered. They are not clear in meaning.
Formatting appears to be insufficient.
Most of the tables and figures have been labelled but contain errors.
Headings are used (preferably numbered).
Formatting appears to be sufficient.
Tables and figures have been labelled with few errors.
Headings are clear in meaning (preferably numbered).
Report is well formatted.
Tables and figures are well labelled (where applicable).
Sources are mostly cited professionally using the appropriate style guide (APA).
Headings are numbered and relate well to the discussions in the section.
Tables and figures are labelled properly (where applicable).
Sources are cited professionally, with a couple of exceptions, using the appropriate style guide (APA).
Report is professionally formatted.
Headings follow a standard convention.
Tables and figures are used and labelled properly.
Sources are cited professionally using the appropriate style guide (APA).
DLE602_Assessment 3 Brief_Source code & report_Module 12 Page 7 of 7
The following Subject Learning Outcomes are addressed in this assessment
SLO c)
Develop critical analysis skills in deep learning research.
SLO d)
Demonstrate collaborative skills to apply deep learning to solve real world problems.
SLO e)
Demonstrate ability to effectively communicate scientific and technical information.

Deep Learning Project Proposal Presentation

DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 1 of 8
Task Summary
In Assessment 1, you read the article entitled ‘Deep Convolution Neural Networks for Twitter Sentiment Analysis’ by Zhao, Gui and Zhang (2018), which can be accessed at: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8244338.
For Assessment 2, in a small group of two to three people, you are required to select and analyse quality research articles similar to the above-mentioned article and identify an interesting project in the world of Deep Learning. Once you have identified the project, you will present your findings in a professional project proposal report and deliver a presentation.
Please refer to the Task Instructions (below) for further details on how to complete this task.
Context
The aim of this assessment is to develop a project proposal for a hypothetical research project. This report will enable you to demonstrate your ability to search for relevant literature, write about other works in the area and design a research project proposal, which you will implement in Assessment 3.
ASSESSMENT 2 BRIEF
Subject Code and Title
DLE602 Deep Learning
Assessment
Deep Learning Project Proposal Presentation
Individual/Group
Group
Length
1,000 words (+/–10%) Report and Presentation
Learning Outcomes
The Subject Learning Outcomes demonstrated by the successful completion of the task below include:
b) Compare and select ways to pre-process signals, images, and texts for natural language, speech recognition, and computer vision applications.
c) Develop critical analysis skills in deep learning research.
d) Demonstrate collaborative skills to apply deep learning to solve real world problems.
e) Demonstrate ability to effectively communicate scientific and technical information.
Submission
Due by 11:55pm AEST/AEDT Sunday end of Module 8.
Weighting
30%
Total Marks
100 marks
DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 2 of 8
Finally, you will communicate details of your project (written and oral) to an audience familiar with Deep Learning.
Task Instructions
In a small group of two to three people, you will research a Deep Learning project of your choice and articulate your findings in a written report and a 5–7 minute audio-visual seminar. You can form a group yourself or your learning facilitator will allocate you to a group and advise you of the students with whom you will be working. Your group will comprise students who have selected a similar topic.
You are required to select, assess and evaluate the information that you include in your written project proposal. The presentation will be an audio-visual submission (please note, online students are only required to film a voice over of the presentation and are not required to film themselves delivering the presentation). The 5–7-minute presentation should provide an engaging explanation of your nominated topic and include the most relevant and absorbing information from your written project proposal.
Report Guidelines
In relation to the report, you need to:
• Prepare a 1,000-word report in which you clearly explain the project that you identified in your literature review and demonstrate a sound application of the project management process;
• Provide a concise description of your project in a statement in your report and state the specific aim(s) or research question(s) that you intend to address;
• Present your report using any standard writing format;
• Include a cover page and table of contents. Note: the cover page needs to include official student names and project name;
• Include an abstract/executive summary;
• State the word count at the end of the report (before the reference section);
• Insert page numbers (the page numbers should appear in the footer of each page); and
• Label any figures and tables in your report with meaningful captions.
Presentation Guidelines
In relation to the presentation, you need to:
• Prepare a 5–7 minute audio-visual presentation that summarises your research. All students need to present for an equal amount time;
• Include a title slide with student details/subject details that clearly introduces your group and the research topic;
• Ensure your presentation is engaging and informative. Your presentation should NOT include the full details contained in your report;
• Use a PDF format for the presentation slides;
DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 3 of 8
• Keep the layout, text sizes and style consistent throughout the presentation. The presentation should reflect your group dynamic;
• Practice the presentation beforehand to ensure it is clear and concise; and
• Include correct reference lists in the appropriate style.
Referencing
It is essential that you use APA style to cite and reference your research. For more information on referencing, visit our Library website at: https://library.torrens.edu.au/academicskills/apa/tool.
Submission Instructions
Compile your written report into a PDF or Word-format and your presentation slides into a PDF format. Submit both the documents using the Assessment link in the main navigation menu for ‘DLE602: Deep Learning Assessment 2’.
Face-to-Face Students
You will present a 5–7 minute audio-visual seminar to the class and submit your PDF document via the Assessment link in the main navigation menu for ‘DLE602: Deep Learning Assessment 2’. Ensure that you have the names and student ID of the members of the group on the front page. The Learning Facilitator will provide feedback via the Grade Centre in the LMS portal. Feedback can be viewed in My Grades.
Online Students
You will record your presentation using the free Zoom program (available as a free online download). Refer to the ‘How to Use Zoom’ PDF document located on Blackboard for more information. Ensure that you have the names and student ID of the members of the group on the front page. Record the group presentation and save it, using the following naming convention: SubjectCodeGroupnumberAssessmentTitle.mp4.
Submit your audio-visual recording and presentation via the Assessment link in the main navigation menu for ‘DLE602: Deep Learning Assessment 2’. The Learning Facilitator will provide feedback via the Grade Centre in the LMS portal. Feedback can be viewed in My Grades.
One submission per group is allowed. Use the following naming conventions:
• SubjectCodeGroupnameAssessmentTitle.pdf
• SubjectCodeGroup nameAssessmentTitle.mp4
References
Zhao, J., Gui, X. & Zhang, X. (2018). Deep convolution neural networks for Twitter sentiment analysis. IEEE Access, 6, 23253–23260. Retrieved from https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8244338
DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 4 of 8
Academic Integrity Declaration
We declare that except where we have referenced, the work we are submitting for this assessment task is our own work. We have read and are aware of Torrens University Australia Academic Integrity Policy and Procedure viewable online at http://www.torrens.edu.au/policies-and-forms
We are aware that we need to keep a copy of all submitted material and their drafts, and we will do so accordingly.
DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 5 of 8
Assessment Rubric
Assessment Attributes
Fail
(Yet to achieve minimum standard)
0–49%
Pass (Functional)
50–64%
Credit (Proficient)
65–74%
Distinction (Advanced)
75–84%
High Distinction (Exceptional)
85–100%
Problem Statement and Aim
• Context of study
• Problem statement
• Specific aims or questions of study
• Link to relevant body of knowledge
• Practical relevance and usefulness
Percentage for this criterion = 20%
Context and problem statement is not properly defined.
Research aims or questions are unclear and/or are not properly justified.
No clear links to the relevant body of knowledge.
Context, problem statement and aims or questions are defined but are loosely coupled.
The above have high level implicit links to the relevant body of knowledge.
Context and problem statement is clearly defined, but the proposed aim and question are not specific to the defined problem.
Justification is provided and attempts have been made to link the proposed questions to the relevant body of knowledge.
Problem, context, aim and research question(s) are clearly stated.
The proposed aim and questions are well justified.
The proposed aim and questions are somewhat linked to the relevant body of knowledge.
The problem statement clearly captures the nuances of the problem succinctly and sets up the proposal in a professional manner.
The proposed aim and questions are clearly linked to the relevant body of knowledge.
Analysis, Synthesis and Application of Literature
• Analysis and synthesis of existing knowledge and related theory
• Application of existing literature
• Project identification
Percentage for this criterion = 25%
The analysis shows poor paraphrasing skills (content is mostly plagiarised).
The synthesis of ideas is weak and inconsistent.
The project is not clearly identified.
The analysis shows inconsistencies.
The synthesis of ideas is inconsistent.
The project is identified but is not clearly explained.
The review and the appraisal of the relevant literature is limited.
The synthesis of ideas is fair.
The project is identified but is not clearly explained.
The review appraises the relevant literature.
The synthesis of ideas is good.
The project is identified and is clearly explained.
The review critically appraises the relevant literature.
The synthesis of ideas is comprehensive.
The project is identified and is clearly explained.
DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 6 of 8
Project Planning and Management
• Plan of activities
• Risk analysis
• Contingency Plan
• Measures to ensure success of project
Percentage for this criterion = 25%
The proposed plan is not feasible.
The plan does not account for the project constraints, time frame, procurement and/or budget.
No risk analysis or contingency plan provided.
The proposed plan is feasible but lacks convincing statements.
The plan does account for the project constraints, timeframe, procurement and/or budget at a very high level.
The risk analysis and contingency plan provided is poor.
Presents a feasible plan, including a basic description of the constraints, time frame and budget.
Some attempt to analyse the risks, set up a contingency plan and identify critical success factors in relation to the project.
Presents a detailed research plan that is clearly feasible within the time frame, budget and other constraints.
Sound analysis of the risks associated with the project.
Sound contingency plan and critical success factors proposed.
Shows good use of project management processes to plan and manage the project work.
Undertakes an excellent review of the risks, contingency plan and critical success factors in relation to the project.
Overall Structure and Flow of Proposal
• Required sections (abstract, introduction, body and conclusion)
• Organisation and structure
• Appropriate argument
Percentage for this criterion = 15%
Writing is difficult to read or follow.
Ideas do not link up well within and/or between paragraphs.
A flawed argument is presented.
No acknowledgement of the audience.
Writing is not consistent, as ideas are only loosely linked within and/or between paragraphs.
A mediocre argument is presented.
The acknowledgement of the audience is too wide.
Writing is easy to follow and clear in meaning. Only minor spelling or grammar mistakes.
Some effort made to tailor the argument and the evidence for the audience.
The report is well organised and the ideas and arguments flow naturally and logically.
The argument and the evidence are appropriate for the target audience.
The report builds a strong and compelling argument for the next assessment and further research and is targeted at the appropriate audience.
DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 7 of 8
Audio-visual presentation
• Delivery
• Content organisation
• Audience awareness
Percentage for this criterion = 15%
Speaks in a low volume and/or monotonous tone, which causes audience to disengage.
Does not clearly define subject and purpose; provides weak or no support of subject; gives insufficient support for ideas or conclusions.
Fails to increase audience understanding or their knowledge of the topic.
Speaks in an uneven volume with little or no inflection.
Attempts to define the purpose and the subject; provides irrelevant examples, facts and/or statistics, which do not adequately support the subject; includes very thin data or evidence
Increases audience understanding and knowledge of at least one point.
Speaks in an uneven volume with little inflection.
Attempts to define the purpose and the subject; provides weak examples, facts and/or statistics, which do not adequately support the subject; includes very thin data or evidence.
Increases audience understanding and knowledge of some points.
Speaks with satisfactory variation in volume and inflection.
Purpose and subject are somewhat clear; includes some examples, facts and/or statistics that support the subject; includes some data or evidence that supports the conclusions.
Increases audience understanding and awareness of most points.
Speaks with fluctuation in volume and inflection to maintain audience interest and emphasize key points.
The purpose and subject are clear; includes pertinent examples, facts and/or statistics; supports conclusions/ideas with evidence.
Significantly increases audience understanding and knowledge of the topic; convinces the audience to recognise the validity and importance of the subject.
The following Subject Learning Outcomes are addressed in this assessment
SLO b)
Compare and select ways to pre-process signals, images, and texts for natural language, speech recognition, and computer vision applications.
SLO c)
Develop critical analysis skills in deep learning research.
SLO d)
Demonstrate collaborative skills to apply deep learning to solve real world problems.
SLO e)
Demonstrate ability to effectively communicate scientific and technical information.
DLE602_Assessment 2 Brief_Report and Presentation_Module 8 Page 8 of 8

Programming Problems

DLE602_Assessment 1 Brief_Source Code and Report_Module 4 Page 1 of 7
Task Summary
For this assessment, you will undertake a Twitter sentiment analysis using a N-Gram model as described in the article entitled ‘Deep Convolution Neural Networks for Twitter Sentiment Analysis’ by Zhao, Gui and Zhang (2018). You can access this article at: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8244338.
Use any two of the five datasets used in this paper and implement Twitter sentiment analysis using Python programming language. Identify and report on the similarities or dissimilarities of the outcomes for two different sources.
Please refer to the Task Instructions (below) for further details on how to complete this task.
Context
Twitter Sentiment Analysis is an automated process whereby text data from Twitter is analysed and segmented into different sentiments (e.g., positive, negative or neutral sentiments). Performing a sentiment analysis on data from Twitter using deep learning models can help organisations understand how people are talking about their brand.
ASSESSMENT 1 BRIEF
Subject Code and Title
DLE602 Deep Learning
Assessment
Programming Problems
Individual/Group
Individual
Length
500 words (+/–10%) and Source Code
Learning Outcomes
The Subject Learning Outcomes demonstrated by the successful completion of the task below include:
a) Build, train and apply deep learning models to real-world tasks.
b) Compare and select ways to pre-process signals, images, and texts for natural language, speech recognition, and computer vision applications.
Submission
Due by 11:55pm AEST/AEDT Sunday end of Module 4.
Weighting
30%
Total Marks
100 marks
DLE602_Assessment 1 Brief_Source Code and Report_Module 4 Page 2 of 7
In the above-mentioned paper, Zhao, Gui and Zhang (2018) introduced the concept of using Deep Convolution Neural Networks for Twitter Sentiment Analysis. The authors also briefly described how the N-Gram model applies to the process. They conclude that Deep Convolution Neural Networks, which use pre-trained word vectors, can perform the task of Twitter sentiment analysis well. They used five different datasets to prove their point.
You will focus on the development of a basic Twitter Sentiment Analysis system using the N-Gram probabilistic language model. You will demonstrate your understanding of language processing models and your ability to develop systems using those models. You will also demonstrate your communication skills by drafting a short report.
Task Instructions
To complete this assessment task, you will need to read the article entitled ‘Deep Convolution Neural Networks for Twitter Sentiment Analysis’ (Zhao & Zhang, 2018) closely.
You are NOT expected to reproduce all the experiments completed in this paper. This paper is provided as a reference to enable you to better understand the context of this assessment and provide you with an idea of the quality of research papers that you need to read as part of Assessments 2 and 3.
The only task you are required to complete in this assessment is to develop a Twitter sentiment analysis technique that uses a N-Gram probabilistic language model.
Your aim is to be able to analyse any twitter texts and classify them into different sentiments, such as positive, negative or neutral sentiments.
If your N-Gram model (Bigram/Trigram) identifies one fourth of the words in a twitter text as positive, classify that twitter text as positive. If your N-Gram model (Bigram/Trigram) identifies one fourth of the words in a twitter text as negative, classify that twitter text as negative. For any other variation to these two scenarios, classify the twitter text as neutral. If you are using Bigram for positive twitter texts, use the same for negative twitter texts. Similarly, if you are using Trigram, use it for both positive and negative twitter texts.
The authors used five different datasets to prove their points. You need to use two of the five datasets to implement your solution. You do NOT have to use all five datasets.
Use Python as the programming language for this natural language processing assessment. The code must be well formatted and conform to Python naming conventions. You also need to provide sufficient comments in the code.
You are also required to prepare a 500-word report highlighting the similarities or dissimilarities of the outcomes from two different sources. You can choose to divide the word limit into multiple paragraphs. Include a short introduction with any critical points that will help your readers to understand the outcomes for your program. Then, briefly describe whether you see similar or
DLE602_Assessment 1 Brief_Source Code and Report_Module 4 Page 3 of 7
different trends, in terms of positive, negative and neutral twitter sentiments, in both of your datasets. Discuss whether your program behaved in the same way for the different datasets.
You will be assessed based on the completeness of your model, the efficiency of the implementation, the coding convention, the quality of code and your articulation of the outcomes.
Finally, you will submit the source code. You must provide a link to the dataset used. Ensure that you include instructions on how to run your code at the top of your main source code file inside a comment block.
Referencing
It is essential that you use APA style to cite and reference your research. For more information on referencing, visit our Library website at: https://library.torrens.edu.au/academicskills/apa/tool.
Submission Instructions
Submit the source code, the link to the dataset you used and your 500-word report in a zip file via the Assessment 1 link in the main navigation menu for ‘DLE602: Assessment 1’ by 11.55 pm AEST on the Sunday at the end of Module 4 (Week 4).
The Learning Facilitator will provide feedback via the Grade Centre in the LMS portal. Feedback can be viewed in My Grades.
References
Zhao, J., Gui, X. & Zhang, X. (2018). Deep convolution neural networks for Twitter sentiment analysis. IEEE Access, 6, 23253–23260. Retrieved from https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8244338
Jurafsky, D. & Martin, J .H. (2008). Speech and language processing. Boston, MA: Pearson. Retrieved from https://web.stanford.edu/~jurafsky/slp3/3.pdf
Academic Integrity Declaration
I declare that except where I have referenced, the work I am submitting for this assessment task is my own work. I have read and am aware of Torrens University Australia Academic Integrity Policy and Procedure viewable online at http://www.torrens.edu.au/policies-and-forms
DLE602_Assessment 1 Brief_Source Code and Report_Module 4 Page 4 of 7
I am aware that I need to keep a copy of all submitted material and their drafts, and I will do so accordingly.
DLE602_Assessment 1 Brief_Source Code and Report_Module 4 Page 5 of 7
Assessment Rubric
Assessment Attributes
Fail
(Yet to achieve minimum standard)
0–49%
Pass (Functional)
50–64%
Credit (Proficient)
65–74%
Distinction (Advanced)
75–84%
High Distinction (Exceptional)
85–100%
Completeness and efficiency
• The implementation covers all requirements.
• The whole system is easy to use and run.
Percentage for this criterion = 25%
None of the requirements have been implemented.
The system does not function properly or is extremely buggy.
An extreme level of manual configuration is required to run the system. Additionally, the configuration does not work.
One or two major requirements have been implemented.
The system does not function properly. No exception handling has been implemented.
Users are required to follow a lengthy configuration manual to run the system.
All but one or two major requirements have been implemented.
The system functions only if certain additional conditions are met. Basic exception handling has been implemented, but it is not thorough.
Users are required to follow a short configuration manual to run the system.
Most of the major requirements have been implemented.
The system functions without any additional conditions needing to be met. Basic exception handling has been implemented, but it is not thorough.
Users are only required to copy the necessary data in the right locations.
All of the major requirements have been implemented.
The system functions properly. Exceptions are handled very well.
Users can run the system without any configuration.
Coding convention and quality of code
• The code follows a consistent and well-formatted programming convention
• The code contains sufficient comments
The code is not formatted.
Little or no comments are provided.
The naming of the methods or variables is inconsistent.
There are significant errors in the format of the code and the naming of the methods or variables.
There is a significant lack of useful comments.
The code is generally well written, but there is some room for improvement.
There are more than five errors but less than eight errors in terms of the naming conventions and the format of the code.
The code is generally well written.
There are more than two errors but less than five errors in terms of the naming conventions and the format of the code.
The code is expertly written.
There are no more than two errors in terms of the naming convention and the format of the code.
DLE602_Assessment 1 Brief_Source Code and Report_Module 4 Page 6 of 7
Percentage for this criterion = 25%
No naming convention is followed.
There is a reasonable amount of useful comments.
There is a sufficient amount of useful comments.
There is a sufficient amount of useful comments.
Accuracy of outcomes
• The code produces the correct results.
• The code behaves the same way, independent of the dataset.
Percentage for this criterion = 25%
The code cannot classify any Twitter texts into sentiments, such as positive, negative or neutral sentiments.
The code cannot classify the Twitter texts for any dataset.
The code can only classify very selective Twitter texts correctly into sentiments, such as positive, negative or neutral sentiments.
The code demonstrates the above-mentioned behaviour for both the datasets.
The code can reasonably classify the Twitter texts correctly into sentiments, such as positive, negative or neutral sentiments.
The code demonstrates the above-mentioned correct behaviour for one dataset but not for the other dataset.
The code can classify 70% of the Twitter texts correctly into sentiments, such as positive, negative or neutral sentiments.
The code demonstrates the above-mentioned correct behaviour for both the datasets.
The code can classify 85% of the Twitter texts correctly into sentiments, such as positive, negative or neutral sentiments.
The code demonstrates the above-mentioned correct behaviour for both the datasets.
Effective written communication
• Writing skills.
• Highlighted the similarities or dissimilarities of the outcomes from two different data sources.
Percentage for this criterion = 25%
Poor writing skills. Additionally, the articulations are not clear at all.
• Lacks overall organisation.
• Very difficult to follow.
• Grammar and spelling errors make it difficult for the reader to interpret the text in many places.
Writing is readable; however, it is difficult to comprehend the information presented.
• Not well organised for the most part.
• Difficult to follow.
• Choice of words needs to be improved.
• Grammatical errors impede the flow of communication.
Writing is readable and it is reasonably easy to comprehend the information presented.
• Organised for the most part.
• Difficult to follow.
• Words are well chosen; however, some minor improvements are needed.
• Sentences are mostly grammatically
Writing is good and it is easy to comprehend the information presented.
• Well organised.
• Cohesive and easy to follow.
• Words are well chosen.
• Sentences are grammatically correct and free of spelling errors.
Writing is excellent, short, sharp and to-the-point and easily digestible.
• Exceptionally organised.
• Highly cohesive and easy to follow.
• Words are carefully chosen that precisely express the intended meaning and support reader comprehension.
DLE602_Assessment 1 Brief_Source Code and Report_Module 4 Page 7 of 7
Failed to highlight the similarities or dissimilarities of the outcomes from the two different data sources.
Attempted to highlight the similarities or dissimilarities of the outcomes from the two different data sources. However, it is not thought provoking or insightful.
correct and contain few spelling errors.
Attempted to highlight the similarities or dissimilarities of the outcomes from the two different data sources. It is reasonably thought provoking or insightful.
Attempted to highlight the similarities or dissimilarities of the outcomes from the two different data sources. It is thought provoking or insightful.
• Sentences are grammatically correct and free of spelling errors.
Attempted to highlight the similarities or dissimilarities of the outcomes from the two different data sources. It is thought provoking, insightful and discovered something very unique from their experiments.
The following Subject Learning Outcomes are addressed in this assessment
SLO a)
Build, train and apply deep learning models to real-world tasks.
SLO b)
Compare and select ways to pre-process signals, images, and texts for natural language, speech recognition, and computer vision applications.

HW 2 – Design a Database

HW 2 – Design a Database
Hide Assignment Information
Instructions
After reading chapter 5, and (especially) the supplementary reading, “Basic Database Concepts…”, you should have an understanding of relational databases. This HW has you apply that knowledge in this week’s assignment by having you think about the following problem that can be solved with database tables:

Imagine that you have to design a database that would match information about job postings and internship opportunities for candidate NYU graduating students (So, instead of matching patrons to books as in the reading, you are matching students to jobs for this HW)

Assume that you currently have separate sets of information (data) about:

-Typical student information such as their identities, their grades, their courses taken, and other information, etc.

-Typical information about job postings and/or internships, such as role, requirements, location, paid/unpaid, and other characteristics, etc.

1) You would like to bring all of this information together in a relational database system. Consider what data elements or variables do you think are necessary?

2) How would you structure distinct tables? (i.e. what would constitute a row in your table(s)?)

3) How would you ensure information is stored efficiently?

4) What keys would you use to relate tables to each other? (i.e. Describe how information in one table would link with information in another table)

5) If you wanted to add the capability of ‘automatically’ matching students to jobs and vice versa, explain via an illustrative example, how this automatic matching might work for your design.

Just as the reading illustrated sample tables, and their relationships, your HW submission should show sample tables and relationships — so that I can understand your design, and how your design would work to solve the task at hand.

Big Data and related discussion

Week 2 – Big Data and related discussion
Imagine the following scenario:

You (i.e. you personally) are tasked with calculating the average from a set of numbers. Can you do it? I expect you would answer Yes. However, what if you had to calculate this average from a set of 1000 raw numbers, and you have to do it by hand – no calculators or other electronic means. You could still do it, but it would take a long long time. Is there a better way?

A better way would be to distribute the work. You round up 100 other students, and each of you will now calculate, by hand, an average of a set of only 10 numbers. So we’ve taken the 1000-number dataset and given each of the 100 students 10 numbers to work with. Now, the task is relatively easy, no?

And when each of you comes up with your average from the 10 numbers, we can collectively then take the average of the averages — and that would be our final answer. And we’re done.

Several things to note — The long computation done by one person would take a long time to finish. That’s how a traditional Relational Database Management System (RDBMS) would do it. Traditional database systems do things in sequence and it can take a long time if it’s a lot of data. In contrast to an RDMBS, a BigData environment will distribute the task. Here’s how it’s different using BigData setup — The 100 students is analogous to 100 computing nodes, each node working on a piece of the problem, each node an independent computer. The distribution of work, and the collection of intermediate averages is like the MapReduce function you’ve seen in the reading. In MapReduce, work is mapped out, and then reduced back. Note also that 100 students can work in parallel, or independently, or simultaneously. That’s analogous to MPP or multi-parallel-processing. And that’s why the answers can come back much much faster. BigData can compute really really fast. Furthermore if one computing node (student) crashes (falls ill), the work need not stop. If a node goes down, it’s not really a big deal. That’s analogous to computing nodes being considered commodity components – i.e. cost effective hardware (cheap labor).

If you keep this analogy in mind, about how a BigData environment is different than a traditional computation, you’ve got the key concept of how it works, why it’s fast, and why it can be cost-effective.

For the discussion this week, think of how the “3 V’s” of BigData and how each of these V’s and related concepts would apply to the problem-scenario that you used in part 1 of this week’s HW.

How might a BigData approach be used to help match students with job opportunities, and vice versa? Discuss . . .

ITECH2301-Network Architecture and Design

Network Design Assignment
ITECH2301-Network Architecture and Design
CRICOS Provider No. 00103D itech2301_ass2.doc- Network Design Assignment, Semester 1, 2021 Page 1 of 5
Due Date
Week 11 on Friday at 23:55
Worth
20% (Marked out of 100 marks)
Type
Type A
Assessment Objective
 The report helps you grasp the fundamental concept of network design and acquire the
knowledge on the techniques required for developing both logical and physical network designs.
 The presentation enables presentation, oral communication and team skills to be exercised as
well as providing an opportunity to research a specific topic.
 Learning Outcomes Assessed:
 K4. Describe the technologies and architecture of LANs, Wireless LANs and WANs.
 K5. Identify the principles of LAN design.
 A1. Analyse and design LAN architecture for organisational requirements.
 S1- Analyse data communication and networking technologies in today’s Internet.
Network Design Case
Accurate Accounting is an Australian regional accounting firm having three local offices
located in Sydney, Adelaide, and Queensland. The company is constructing two adjacent
buildings: (i) a three-story office building comprising 80 rooms and (ii) a single-story
administration building with 20 rooms in Victoria as its main headquarter. The office building
houses 80 computers, with additional 20 computers in the administration building. You are
required to design a network (LAN) for the Victoria headquarter enterprise campus, which
connects the three local offices. Therefore, you need to consider the WAN access in the LAN
design for the headquarter enterprise campus.
The new network will house a data centre, the e-commerce edge, and 8 printers. 6 printers will
be installed in the different rooms of the office building, while the other two are to be installed
in the administration building. An employee is allowed to have a printing service with any
printer through the new network. Employees will bring their own mobile devices (e.g.,
laptops, smartphones, tablets) to work. Employees will use them to access required
information such as their work email, required documents, and Internet through wireless
communication facilities (Wi-Fi access points).
Network Design Assignment
ITECH2301-Network Architecture and Design
CRICOS Provider No. 00103D itech2301_ass2.doc- Network Design Assignment, Semester 1, 2021 Page 2 of 5
You will also require to make some assumptions, so be sure to document your assumptions
and explain why you have designed the network in this way.
Requirements
There are two parts of the requirements for this assignment – a) Report and b) Presentation.
Hand drawn layouts for both logical and physical designs are fine. However, if you like, you
would use ConceptDraw (https://conceptdraw.en.softonic.com/) or SmartDraw
(www.smartdraw.com) or any other network design software to draw the layout of logical and
physical network designs.
a) Report [70 marks]
The report should be no more than 10 pages and needs to consider the following design
tasks:
Design Tasks:
T1. Using the building-block network design process, develop a logical design of the new
network for the Victoria headquarter enterprise campus that considers the seven
network architecture components. Remember to consider the expected growth of the
company. For the logical design, you need to consider the following items:
[25 marks]
1. Network architecture components
2. Application systems
3. Network users
4. Categorizing network needs
5. Deliverables
T2. Design the physical design of the network based on the logical design completed in
Task T1. Note, you do not need to develop an alternative design. For the physical
design, you need to consider the following items:
[20 marks]
1. Designing client and servers
2. Designing circuits
3. Network design tools
4. Deliverables
T3. Provide a short description of how the LAN of headquarter can be connected with the
LANs of the local offices via WAN.
[5 marks]
Network Design Assignment
ITECH2301-Network Architecture and Design
CRICOS Provider No. 00103D itech2301_ass2.doc- Network Design Assignment, Semester 1, 2021 Page 3 of 5
T4. Briefly describe how you will minimise the interference from Wi-Fi access points
(APs) on different floors.
[10 marks]
T5. You will make some assumptions; therefore, document your assumptions and explain
why you have designed the network in this way.
[10 marks]
b) Presentation [3O marks]
You need to produce a presentation consisting of eight PowerPoint slides based on your
report and the relevant assessment criteria. The presentation time is 10 minutes. The
presentation will be given in Week 12’s timetabled tutorial.
Online students can provide the presentations through either an appropriate online video
conferencing technique (e.g., Teams) or adding voice-over to their PowerPoint presentation
slides.
Assessment Feedback
Student
Assessment criteria for the report:
Elements Maximum
Marks
Marks
Obtained
T1. Logical design (need analysis)
– Network architecture components 3
– Application systems 4
– Network users 4
– Categorizing network needs 4
– Deliverables 10
T2. Physical Design (technology design)
– Designing client and servers 3
– Designing circuits 4
– Network design tools 3
– Deliverables 10
T3. A short description of the WAN connection 5
T4. Minimising the interference from Wi-Fi access points 10
T5. Assumptions and their explanation 10
Total marks for the report 70
Network Design Assignment
ITECH2301-Network Architecture and Design
CRICOS Provider No. 00103D itech2301_ass2.doc- Network Design Assignment, Semester 1, 2021 Page 4 of 5
Comments
Assessment criteria for the presentation:
Elements Maximum
Marks
Marks
Obtained
Content – summary in relation to topic 5
– interesting, informative, & useful
information 4
– reflective thinking about the design 8
Communication – use of language 2
– main points emphasised 2
– spoke to whole audience, good eye
contact 2
– voice volume, pitch, variety 2
Presentation – personal presentation 2
– quality of slides 3
Total marks for the presentation 30
Total Marks for Assignment 2 100
Total Worth [20%] 20
Comments
Supporting Materials
Please look at Weeks 6-8 study materials, including lecture notes, tutorial problems, and their
solutions, online materials, and relevant sections of the prescribed text. You also need to use
Internet resources. Please see the assessment criteria carefully.
Network Design Assignment
ITECH2301-Network Architecture and Design
CRICOS Provider No. 00103D itech2301_ass2.doc- Network Design Assignment, Semester 1, 2021 Page 5 of 5
Submission
You need to submit two files – (i) your assignment report in either Microsoft Word or PDF format
and (ii) presentation slides. Please create a zip file, namely Assignment2.zip using these two files,
and submit it via Moodle. Please refer to the “Course Description” for information regarding late
assignments, extensions, special consideration, and plagiarism. A reminder of all academic
regulations can be accessed via the university’s website. URL: http://federation.edu.au/currentstudents/
essential-info/publications/handbook.