Skip to content

Latest commit

 

History

History
58 lines (38 loc) · 2.46 KB

README.md

File metadata and controls

58 lines (38 loc) · 2.46 KB

AI From Scratch

This repository contains implementations of various AI and machine learning concepts, architectures, and exercises built from scratch. It serves as a learning resource for understanding the underlying principles of artificial intelligence and machine learning algorithms.

Repository Structure

Architectures

This directory contains implementations of different neural network architectures and machine learning models.

  • convolutional_neural_network_reinforcement_learning_monte_carlo_tree_search_selfplay_alphazero_tictactoe.ipynb: Implementation of a convolutional neural network with reinforcement learning using Monte Carlo Tree Search and self-play, similar to AlphaZero, applied to Tic-Tac-Toe.
  • logistic_regression.ipynb: Implementation of logistic regression algorithm.
  • lstm.py: Long Short-Term Memory neural network implementation.
  • diffusion.py: Diffusion model implementation.
  • linear_regression.py: Linear regression implementation.
  • bigram.py: Bigram language model implementation.
  • multiple_linear_polynomical_sinus_etc_regression_and_gradient_descent.ipynb: Implementation of various regression techniques including multiple linear, polynomial, and sine regression with gradient descent.

Transformer

  • transformer.py: Implementation of the transformer architecture.
  • einops.py: Implementation of einops operations for tensor manipulations.
GPT-2
  • train_gpttwo.py: Training script for a GPT-2 style model.
  • play.ipynb: Interactive notebook for playing with the trained GPT-2 model.
  • fineweb.py: Fine-tuning utilities for web data.
  • hellaswag.py: Implementation for the HellaSwag benchmark.
  • input.txt: Training data for the model.

Exercises

  • hyperplane_classifier_of_clothes.py: Exercise implementation of a hyperplane classifier for clothing items.

Getting Started

To use this repository, clone it to your local machine and explore the different implementations. Each file is self-contained and includes the necessary code to understand and run the respective algorithm or model.

git clone https://github.com/yourusername/ai-from-scratch.git
cd ai-from-scratch

Prerequisites

  • Python 3.x
  • NumPy
  • PyTorch (for some implementations)
  • Jupyter Notebook (for running .ipynb files)

License

This project is available for educational purposes.

Acknowledgments

  • Inspired by the desire to understand AI and machine learning concepts from first principles.