"Building and Evaluating a CNN Classifier on CIFAR-10 Dataset"
- Subject Code :
CO3113
- University :
Southern Cross University Exam Question Bank is not sponsored or endorsed by this college or university.
- Country :
India
CO3113 Assignment 2
This coursework contributes 20% towards your CO3113 marks. All requirements are compulsory and must be implemented.
Plagiarism and Collusion
Plagiarism and/or collusion will result in penalties that might go beyond this assignment: https://www2.le.ac.uk/offices/sas2/assessments/plagiarism/penalties.
Late Submission and Mitigating Circumstance
Late submission penalties will be applied. Read the sections on late coursework submission in your student handbook or here: https://www2.le.ac.uk/offices/sas2/assessments/late-submission.
Accepted mitigating circumstances are the only way to waive late submission penalties: https://www2.le.ac.uk/offices/sas2/regulations/mitigating-circumstances.
Submission Instructions
Submit your solution on Blackboard by Thursday the 28th of March, 17:00 UK time. Submissions will not be accepted by any other means (e.g., via email).
- You must submit a single ipynb file and a single pdf The file name must be your usernames (i.e., ka388).
- You may try it as many times as you like before the Only the last submission attempt will be marked.
- Code must execute without modifications. Your project must execute If not, you will lose 20% of the marks assigned to this part of the coursework.
- You must write your The submitted code from any existing sources will be treated as plagiarism and receives 0 marks.
AI Policy
Red light for the Generative AI tools, which means Generative AI tools, such as ChatGPT, shall not be used. This is an assessment of the independent critical thinking and core theoretical understanding, which includes the core theory and programming skill assessment. Therefore, the students must demonstrate the core knowledge and independent understanding without the aid of AI.
Tasks and Marking Scheme
This assignment requires to build a Convolutional Neural Network (CNN)-based classifier for a classification task on the CIFAR-10 dataset. Following that, you should submit a report detailing the network design and analysing its performance.
Part |
Requirements |
1. Code of the CNN classifier (70%) |
Data download and preparation should be carried out and executed directly. (5%) The training process must be executed and clearly presented. (15%) The testing must be executed and results shown. (15%) Accuracy must be calculated and presented directly. (15%) The models classification accuracy must be appropriate, which is >50%. (20%) |
2. Technical Report (30%) (less than 800 words and 4 pages) |
Detailed structure of the convolutional neural network, including the output size of each layer. (10%) Explanation of the choice of the loss function and illustration of the changes in training and testing loss using a figure. (10%) Observation of how the accuracy changes during the training process and a detailed analysis of these changes. (10%) |
