Scribd
Upload
2 views

Assignment #1 CNN - Machine Learning

The assignment for BITS F464 - Machine Learning requires students to implement a Convolutional Neural Network (CNN) for image classification, focusing on understanding CNNs through practical application. Students must work in groups of up to three, select a non-binary image classification problem, and compare their CNN solution with a non-CNN approach. Deliverables include a detailed report, problem analysis, and code files, all submitted as a single zipped file by April 9, 2025.

Uploaded by

uzumakinarutosaga0
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Assignment #1 CNN - Machine Learning

The assignment for BITS F464 - Machine Learning requires students to implement a Convolutional Neural Network (CNN) for image classification, focusing on understanding CNNs through practical application. Students must work in groups of up to three, select a non-binary image classification problem, and compare their CNN solution with a non-CNN approach. Deliverables include a detailed report, problem analysis, and code files, all submitted as a single zipped file by April 9, 2025.

Uploaded by

uzumakinarutosaga0
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

BITS F464 - Machine Learning

II Semester 2024-2025
Assignment #1
Weightage: 10%
Due Data: 09th April 2025

Convolutional Neural Networks (CNN)


CNNs have revolutionized Image related applications in the past decade. In this
assignment you are required to implement a CNN for image classification. The
objective of the assignment is to understand CNNs through implementation and
problem solving.

As part of the assignment, you are required to:


1. Implement from scratch a CNN using C/C++/Java
2. Pick up an image classification problem (ensure that you have enough labelled data to
train a CNN and that it is not a binary classification problem)
3. Use your implementation to solve the identified problem
4. Compare your CNN solution with non-CNN solution which requires linearization of
image.

You can work in groups of maximum two (03) students.


What you need to submit?
- A detailed report on CNN covering theoretical aspects.
- Details of the image classification problem along with results/analysis
- Code file(s)

Submit everything (on NALANDA) as a single zipped file with file name Group#XX.zip.

Please note: DO NOT send mails requesting for implementation in Python or R. Also, no
request for allowing more than 3 students in a group will be entertained.

Navneet Goyal

You might also like