we will use supervised learning techniques to classify the independent component (IC) images of resting state functional magnetic resonance imaging (rs-fMRI) scans as Noise and Resting state network (RSN)

Contribution for Traffic Sign Detection and Warning System in real time with Custom Dataset & YOLOv8.

Easy-to-Use library to recognize faces, train the model, provide predictions

Explore credit card approval prediction through data analysis and machine learning. Preprocess data, train logistic regression models, and optimize hyperparameters. Learn data preprocessing, feature engineering, model training, and evaluation. Dive into the world of machine learning with Python and popular libraries.

A computer vision project using deep learning to detect face masks in live video. Accurate and efficient, it overlays results on the video feed, indicating mask presence. Monitors compliance in public spaces, workplaces, and healthcare settings for enhanced safety.

Simpler Distil-Whisper

A portfolio of all of the various Kaggle competitions and projects I have participated in, which mostly revolves around machine learning.

batchboost: regularization for stabilizing training with resistance to underfitting & overfitting

Single Headed Attention RNN - "Stop thinking with your head"

zoofs is a Python library for performing feature selection using a variety of nature-inspired wrapper algorithms. The algorithms range from swarm-intelligence to physics-based to Evolutionary. It's easy to use , flexible and powerful tool to reduce your feature size.

This is a web app (using eel-python) that is used to detect emotions using deep learning. This web app can also train a model.

A learning rate range test implementation in PyTorch

Blackbeard - Smart glasses blackjack AI project for Harvard Wearable & Computer Vision Class DGMD E-14 Fall 2021

Developing ChatBot [ open source ]

A lambda function split preprocessed data into training and validation used for starting a training job within AWS SageMaker.

AI model training to produce arts in GBA FE style

Run remote machine learning model training jobs right from the command line.

A machine learning project for predicting credit card approvals using logistic regression.

This repository contains code for a binary image classification model to detect pneumothorax using the ResNet-50 V2 architecture. It includes essential steps such as dataset splitting, image augmentation, model training, and a Streamlit application for user image upload and prediction.

Implements an entire machine learning pipeline to train and evaluate a Random Forest Classifier on labeled gait data for walking. Data generated during the experiment has led to helpful insights in to the problem domain.