liticx/solve-by-hand

Demystify AI concepts: hand-solved problems translated into code for clarity.

Solve by Hand (Deep Learning & AI Fundamentals)

This repository contains a series of exercises designed to help understand and implement fundamental concepts of neural networks, deep learning, and AI techniques. Each example builds upon the previous one, introducing more complex structures and concepts.

Examples

Below is a list included in this project with links to detailed explanations:

• Basics
• Networks
• Normalization and Regularization
• Advanced Concepts & Experiments

Getting Started

To get started with these exercises, clone the repository and navigate to each exercise's directory:

git clone https://github.com/jeremy-london/solve-by-hand.git
cd solve-by-hand

Each directory contains a README.md with instructions specific to the exercise, along with any necessary code files and resources.

Prerequisites

Before you begin, ensure you have the following requirements installed:

• Python 3.10 or higher
• NumPy library You can install NumPy using pip or using poetry:

pip install -r requirements.txt

Contributing

Contributions to improve the exercises or add new ones are welcome. Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests.

License

This project is licensed under the UNLICENSED License - see the LICENSE file for details.

Acknowledgments

We'd like to extend our deepest gratitude to Tom Yeh (@doubleshow), Associate Professor of Computer Science at the University of Colorado Boulder, for providing the handwritten problems and examples that have been pivotal in the development of these neural network exercises.

His contribution has greatly enriched the learning experience for students and practitioners alike.