Machine Learning assignments, Machine Learning (IE500618) course, fall 2022.

Machine Learning Practical - Coursework 2: Analysing problems with the VGG deep neural network architectures (with 8 and 38 hidden layers) on the CIFAR100 dataset by monitoring gradient flow during training. And exploring solutions using batch normalization and residual connections.

Experimented with multi layer perceptron with different hyperparameters

Image classification using CNNs

Classification project based on custom classes of CIFAR-100 dataset according to my student ID number.

This project explores diverse approaches to image classification on the CIFAR-100 dataset. Starting from traditional CNNs combined with KNN classifiers, it progresses to ResNet50 with FCNN and culminates in the cutting-edge Vision Transformer (ViT) model.

A model based on CNN (Convolutional Neural Networks) in order to classify the CIFAR100 dataset, composed by 60,000 32x32 color images labeled over 100 categories.

A Kaggle Community Competition. Can you craft a deep learning model that is better than a bird at classifying 6 remarkable North American butterflies? https://www.kaggle.com/c/yum-or-yuck-butterfly-mimics-2022

AI based image classification inspired MobileNet V2 architecture by implementing changes in base architecture and details about using it as a quick response model (proposition) for rapid application as well as comparing it with other models for the same application.

Recommender systems, 2017-18

Multinomial Naive Bayes and Gaussian Naive Bayes for 20 news groups and Image Classification. NN Cifar100 Example

Deep learning projects completed for graduate class ECE472

Using a convolutional neural network on different datasets.

Evaluation Practices done for the Deep Learning subject

Programming assignments from Deep Learning Class (CSE496/896)

python code, notebooks and Images used for AI502 Midterm Project.