Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neural Networks" https://arxiv.org/abs/1506.01186 for PyTorch framework

Implemented GPT from scratch

Prepare-Training-Model-Yolo11

Lightweight SegFormer3D-inspired 3D Transformer for right-ventricle segmentation in cardiac MRI (evaluated on the public M&Ms-2 multi-center, multi-view dataset).

Deep Neural Network built from scratch to tackle ML binary classification predicting Titanic survival (Kaggle Competition). Best DNN AdamW 77.03% and best RF 78.95%.

The goal of this project is to devise an accurate CNN-based classifier able to distinguish between Cat and Dog in images where the animal is predominant.

ECE-666: Applied Optimization methods for Machine Learning. This repository contains PyTorch implementations for a variety of recent optimization algorithms in deep learning.

ResNet-18 CNN to classify MRI images into four categories: glioma, meningioma, pituitary, and no tumor.

Cat pain recognition assistance based on ResNet18 with AdamW and focal loss

Implementing and fine-tuning BERT for sentiment analysis, paraphrase detection, and semantic textual similarity tasks. Includes code, data, and detailed results.