Skip to main content

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.

This repository is a hands-on ML engineering reference built around one principle: the best way to learn machine learning is to build complete, working systems. Every project follows the same reproducible architecture — dataset handling, preprocessing pipelines, trained models, Jupyter notebooks, and a deployable Flask API — so you spend time learning ML concepts rather than figuring out folder layouts. The repository powers two external learning platforms and serves as a backend reference for reproducible ML workflows.

Two sections, one system

The repository is organized into two top-level sections:
  • ML_To_Train/ — 100+ end-to-end ML projects covering supervised learning, unsupervised learning, computer vision, NLP, generative AI, conversational AI, time series, and reinforcement learning. Each project is self-contained with its own dataset, trained model artifacts, preprocessing pipeline, and Flask API.
  • ML_from_scratch/ — Implementations of ML algorithms built from first principles without high-level library abstractions, designed to build deep understanding of how models work internally.
Whether you are a student working through ML fundamentals, an engineer looking for reproducible project templates, or a researcher who needs a structured backend for ML experimentation, this repository gives you working code at every stage of the pipeline.

Where to go next

Project structure

Understand the standard directory layout shared by every project in the repo.

Quickstart

Clone the repo, install dependencies, and make your first prediction in minutes.

ML from scratch

Explore algorithm implementations built without high-level ML abstractions.

Supervised learning projects

Browse regression and classification projects using real-world tabular datasets.

Project categories

The ML_To_Train/ section covers nine categories across the full ML spectrum:
CategoryRangeDescription
Supervised Learning01–29Regression and classification on tabular data
Unsupervised Learning09, 24–25Clustering, anomaly detection, topic modeling
Recommendation Systems22Personalized recommendation models
Computer Vision & Deep Learning30–34Image classification using CNNs
Natural Language Processing40–41, 16Text analysis and classification
Generative AI50–52, 87Text and image generation systems
Conversational AI & Chatbots60–65Rule-based and AI-powered chat systems
Time Series & Forecasting70, 72Sequential and temporal data modeling
Reinforcement Learning71, 80–86Agent-based learning and game environments

System flow

The diagram below shows how the repository fits into the broader ecosystem, from raw ML projects through to the external learning platforms it powers.

Build docs developers (and LLMs) love