42028: Deep Learning and Convolutional Neural Networks

Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

42028: Deep Learning and Convolutional Neural Networks
Autumn 2026
ASSIGNMENT-1 SPECIFICATION
Due date:Friday 11:59pm, 20 March 2026
Demonstrations :If required.
Marks:30% of the total marks for this subject
Submission:
1. A report in PDF (5-pages max) (5%)
2. Google Colab/iPython notebooks (25%)
Submit to Canvas assignment submission
Note: This assignment is individual work.

Summary

This assessment requires you to develop two different classifiers namely: SVM and Neural Network for handwritten mathematical symbol classification.

The features to be used for classification are: Histogram-Of-Oriented-Gradients (HoG), Local Binary Pattern (LBP), Raw images/pixels, Any other feature (optional).

Students need to provide the code (Colab/ipython Notebook) and a final report for the assignment, which will outline a brief comparative study of the classifier’s performance.

Assignment Objectives

The purpose of this assignment is to demonstrate competence in the following skills.


  • To ensure firm understanding of basic machine learning basics. This will facilitate understanding of advanced topics.
  • To ensure that students understand the basics of image classification, feature extraction using the traditional machine learning techniques.Page 


Tasks:
Description:
1. Implement an image classifier using SVM.
2. Implement an image classifier using Artificial Neural Network (ANN).
3. Compare the two implementations in terms of classification accuracy and top choices.

Write a short report on the implementation, linking the concepts and methods learned in class, and provide comparative study on the accuracies obtained from the combination of different classifiers and features.

IMPORTANT: Features to be used: ALL from the list given below
a. HoG
b. LBP
c. Raw image/pixels value and any other feature you like (optional)

Dataset to be used: Dataset to be generated by students using the instructions provided via Canvas.

Report Structure:
The report should include the following sections:
1. Introduction: Provide a brief outline of the report and briefly explain the features and classifier combination used for experiments.
2. Dataset: Provide a brief description of the dataset used with some sample ,images of each class.
3. Experimental results and discussion:
a. Experimental settings: Provide information on the classifier settings (e.g: SVM: kernel and other parameters used in SVM classifier; ANN: number of input neurons/nodes, activation function, loss function, output layer information etc.)
b. Experimental Results:
i. Confusion matrix for the highest accuracy achieved, with a very short description, with some result image sample.

ii. Comparative study: sample table format 

Classifier/Feature
 HOG
 LBP
 Raw Input
SVM


ANN


iii. Discussion: Provide your understanding on why there was an error in the accuracy, and difference in the performance of the
classifiers. You may also include some image samples which were wrongly classified.Page 3 of 4
4. Conclusion: Provide a short paragraph detailing your understanding on the experiments and results.
Deliverables:
1. Project Report (around 5 pages)

2. AWS Sagemaker or Colab or IPython notebooks, with the code. The code should run on Sagemaker /Google Colab. The submitted notebook should also have the output visible after running each code cell.

3. To be safe, you can also download the code notebooks as PDF and submit it along with the code notebooks.

Additional Information:

Dataset Generation

Please check the addendum on Canvas, which provides details on how to generate the dataset.

Please note: Every student will get one set of 10 different classes with a unique set of images inside each class folder. The classes and images might vary depending on your student ID. For a specific student ID, the system will generate the same set of data every time. Make sure to use your set of data for your assignment. This will be cross verified.

Not following the process as outlined above to obtain the dataset, or using a different dataset will result in a 0 (zero) for the complete assignment.

Assessment Submission

Submission of your assignment is in two parts. You must upload a zip file of the Ipython/Colab notebooks and the Report separately on Canvas. This must be done by the Due Date. You may submit as many times as you like until the due date. The final submission you make is the one that will be marked. If your submission cannot be run/tested, it may result in a zeromark. Additionally, the result achieved and shown in the ipython/colab notebooks should match the report. Penalties apply if there are inconsistencies in the experimental results and the report.

PLEASE NOTE 1: It is your responsibility to make sure you have thoroughly tested your program to make sure it is working correctly.

PLEASE NOTE 2: Your final submission to Canvas is the one that is marked. It does not matter if earlier submissions were working; they will be ignored.

Download your submission from Canvas and test it thoroughly in your assigned laboratory session.

Return of Assessed Assignment

It is expected that marks will be made available 2-3 weeks after the submission via Canvas.
Queries

If you have a problem such as illness which will affect your assignment submission contact the subject coordinator as soon as possible.

Dr. Nabin Sharma
Room: CB11.07.124
Phone: 9514 1835

If you have a question about the assignment, please post it to the Canvas discussion forum for this subject so that everyone can see the response.

If serious problems are discovered, the class will be informed via an announcement on Canvas. It is your responsibility to make sure you frequently check Canvas.

PLEASE NOTE : If the answer to your questions can be found directly in any of the following sources:

  • Assignmentspecification
  • Canvas FAQ page à Assignment 1 and General
  • FAQs related to Assignment 1 are provided to clarify and support the assignment requirements and should be considered part of the overall specifications.
  • Canvas discussion board
Please ensure you review these resources before seeking further clarification.

2026-03-30