🎉 Welcome to the Neural Network From Scratch repository! 🧠 Here, you'll find a fantastic tutorial series that takes you on an exciting journey through understanding and implementing neural networks, from the basics to creating your very own machine learning library. 🤖
This tutorial series covers the following chapters:
- Simple Predictor: 💡 Learn how computers are simple predicting machines and implement the concept with a fun example.
- Classifier vs Predictor: 🔄 Explore how a predictor can transform into a classifier with a captivating example.
- Learning Rate: 🏃♂️ Uncover the magic of learning rate and its role in the learning process.
- Sometimes One Classifier is not Enough: 🧩 Discover the XOR problem and why one classifier might not be enough.
- Neuron and Activation Function: 🧪 Examine the structure of a neuron and the vital role of activation functions in neural networks.
- Modeling an Artificial Neural Network: 🎨 Master the art of modeling artificial neural networks.
- Understanding Neural Networks: 🕵️♂️ Peek inside the inner workings of neural networks, modeled after the human brain.
- Matrix Multiplication is Useful: 📐 Unlock the power of matrices in neural network calculations with a 2-input, 2-layer example.
- BackPropagation: 🌊 Dive into the world of backpropagation and its function in neural networks.
Special thanks to Tariq Rasheed's book, Make Your Own Neural Network, which served as a guide for creating these notebooks and chapters. The chapters are freely licensed under the MIT license, so anyone can use them.
This project is distributed under the MIT License. See LICENSE.txt for more information.
Follow me on LinkedIn and keep up to date with my latest projects on GitHub:
