machine-learning-algorithms-from-scratch

This repo is meant to serve as a detailed guide for Machine Learning/AI interviews.

ML-algorithms from scratch using Python. Classic Machine Learning course.

Deepfake Detector is an AI/ML model designed to detect AI-generated or manipulated images.

JABACAT-created machine learning library from scratch.

ML Concept Implementation in C#

A collection of practical machine learning concepts and implementations focused on enhancing understanding through hands-on examples.

A collection of core Machine Learning algorithms implemented from scratch using only NumPy. This project focuses on understanding the inner workings of ML models without relying on libraries like scikit-learn, TensorFlow, or PyTorch.

These are my notes for machine learning

Retail Recommendation System uses deep neural networks to deliver personalized product recommendations based on customer behavior and product data, helping retailers boost engagement, optimize inventory, and drive growth.

Machine learning algorithms implemented from scratch (Linear/Logistic Regression, KNN, Decision Tree, SVM) plus 50+ practical notebooks covering the full ML pipeline — preprocessing, regression, classification, clustering, association rules, and ensemble learning — across 14+ datasets.

Screwing around with Machine Learning

Detect deepfake images and videos with EfficientNet-B0, face extraction, Grad-CAM heatmaps, and a FastAPI REST API for clear analysis