100 ML & AI Projects is a structured, open-source repository containing 100+ machine learning and artificial intelligence implementations — from classical regression to reinforcement learning agents. Every project follows the same consistent architecture: a dataset, preprocessing pipeline, trained model, Flask API backend, and a Jupyter notebook for reproducibility. Use this documentation to understand the project categories, explore individual implementations, and learn how to run or extend any project.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/dronabopche/100-ML-AI-Project/llms.txt
Use this file to discover all available pages before exploring further.
Quick Start
Set up your environment and run your first ML project in minutes
Project Structure
Understand the standardized architecture shared across all 100+ projects
ML From Scratch
Explore classical algorithms built with NumPy — no sklearn required
Supervised Learning
Regression and classification projects on real-world tabular datasets
What’s inside
This repository is organized into two main sections:- ML From Scratch — 10 classical algorithms implemented from first principles using NumPy: Decision Tree, KNN, Linear Regression, Logistic Regression, Naive Bayes, Neural Network, PCA, Random Forest, SVM, and K-Means Clustering.
- ML To Train — 50+ end-to-end projects covering supervised learning, unsupervised learning, computer vision, NLP, generative AI, conversational chatbots, time series forecasting, and reinforcement learning agents.
Unsupervised & Vision
Clustering, anomaly detection, and CNN-based image classification
NLP & Generative AI
Text analysis, sentiment detection, text generation, and RAG pipelines
Time Series & RL
Stock trend prediction, weather forecasting, and game-playing RL agents
Reference & Pipeline
Full ML pipeline reference: preprocessing, inference, and API integration
Getting started
Choose a project
Browse the
ML_To_Train/ directory. Each numbered folder is a self-contained project with its own requirements.txt and Jupyter notebook.Install dependencies and run
Install dependencies and launch the notebook or Flask API for the chosen project.
All projects are designed for Python 3.10+. Datasets are sourced from Kaggle and Hugging Face — links are provided in each project’s README.