Learning Outcomes to be assessed:
Demonstrate a critical understanding of the theoretical principles and objectives of Deep Learning (DL)
Critically assess and select a range of DL concepts and techniques.
Programmes: MSc Artificial Intelligence (Machine Learning)
7144COMP Report on Theoretical Principles of Deep Learning Assignment-Liverpool University UK
Introduction:
This coursework focuses on the theoretical aspects of deep learning and its practical implications.Associated tools and techniques for undertaking the training and inferencing of a deep learning model for a particular scenario is also covered. For the first part of the coursework, you are required to write a six-page paper (double column IEEE format) on the topic of deep learning and related concepts using the materials taught in the lectures while undertaking independent research to reinforce the conclusions and opinions expressed in your paper. The second part of the coursework focuses on the practical implications and considerations of training a deep learning model while undertaking inferencing. Here you are required to construct a methodology for a given scenario taking into consideration the hardware, data and functional requirements.
Detail of the tasks
1) Deep learning concepts and discussion
BBC Autumn watch has launched a computer vision challenge to develop a deep learning object detection model to track the species of birds visiting gardens throughout autumn. They wish to use standard camera trap equipment which provides still image data with a resolution of 1024 x 768
pixels. You are required to write a research paper using the templated provided on Canvas called(Course work 1 template .docx) and the associated image data (Birds.zip). Please note that the format settings of this template are not to be changed. Your paper must include the following
sections and discussion:
7144COMP Report on Theoretical Principles of Deep Learning Assignment-Liverpool University UK
A) Title – A suitable title which describes your paper.
B) Name and affiliation – Your name and place of study.
C) Abstract – A summary of the whole paper
D) Introduction – Outline the challenge, describe similar research in this area (both deep and non-deep learning approaches), discuss current limitations and provide details of what you propose to do.
E) Background – Must include a discussion on the challenge as outlined by BBC Autum watch, computer vision, deep learning and its role in object detection.
F) Methodology – Must include a data description of the provided dataset, Exploratory Data Analysis (EDA), Data pre-processing, model architecture selection, discussion and justification, model training (hyper parameter selection), inference and evaluation.
G) Discussion – Discussion of the challenge and provide a justification for your proposed methodology for addressing the computer vision task set by BBC Autumn watch for 2020.
H) Future Work – In coursework 2 you will be required to implement your methodology therefore this section should include an implementation and evaluation plan.
You should include graphs and figures in your paper (which can be taken form Jupyter Lab) where appropriate. You will be required to use academic references throughout your paper which should be obtained from sources such as google scholar, Research Gate or arXiv.org. All references must
be stored in Mendeley and inserted into your paper using the Mendeley word plugin.
7144COMP Report on Theoretical Principles of Deep Learning Assignment-Liverpool University UK
What you should hand in
You should submit a single word-processed document via the Assignment Handler in Canvas.The document is to be named as coursework one. docx. The document should be processed using the template provided on Canvas.
NOTE: to enable anonymous marking, do NOT include your name and student ID number in any document.
Marking Scheme/Assessment Criteria
Supporting Material
The following texts are useful additional reading for this module:
- Lecture notes and labs.
- Designated reading material
Extenuating Circumstances
If something serious happens that means that you will not be able to complete this assignment, you need to contact the module leader as soon as possible. There are a number of things that can be done to help, such as extensions, waivers and alternative assessments, but we can only arrange
this if you tell us. To ensure that the system is not abused, you will need to provide some evidence of the problem.
7144COMP Report on Theoretical Principles of Deep Learning Assignment-Liverpool University UK
Academic Misconduct
The University defines Academic Misconduct as ‘any case of deliberate, premeditated cheating, collusion, plagiarism or falsification of information, in an attempt to deceive and gain an unfair advantage in assessment’. This includes attempting to gain marks as part of a team without making a contribution. The Faculty takes Academic Misconduct very seriously and any suspected cases will be investigated through the University’s standard policy
It is your responsibility to ensure that you understand what constitutes Academic Misconduct and to ensure that you do not break the rules. If you are unclear about what is required, please ask.
ORDER This 7144COMP Report on Theoretical Principles of Deep Learning Assignment NOW And Get Instant Discount
Read More :-
7143COMP Academic Paper On Theoretical Principles Of Machine Learning
