Skip to content

COMP 551 Project 3 - Multilabel classification of handwritten digit images

Notifications You must be signed in to change notification settings

preyansh98/Multilabel_Digit_Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Multilabel_Digit_Classification

COMP 551 Project 3 - Multilabel classification of handwritten digit images

This project implements a deep neural network model for a multi-label classification problem on a modified MNIST dataset. The dataset was pre-processed, and the model and hyperparameters (optimizer, learning rate, batch size, number of epochs) were tuned through manual testing and exhaustive grid search to improve accuracy. The combination of hyperparameters resulting in highest validation accuracy was picked, resulting in an accuracy of 99.785 on the public test set on kaggle.

Done with Shayan Sheikh and Matthew Kourlas for COMP 551: Machine Learning at McGill University.

About

COMP 551 Project 3 - Multilabel classification of handwritten digit images

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published