https://github.com/hanzopgp/neuralnetworkfromscratch

This is a multi-layer perceptron build from scratch using numpy and python.
https://github.com/hanzopgp/neuralnetworkfromscratch

artificial-intelligence deep-learning machine-learning multi-layer-perceptron numpy personal

Last synced: 2 months ago
JSON representation

This is a multi-layer perceptron build from scratch using numpy and python.

• Host: GitHub
• URL: https://github.com/hanzopgp/neuralnetworkfromscratch
• Owner: hanzopgp
• License: mit
• Created: 2020-12-15T13:38:30.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2021-02-18T23:55:09.000Z (over 5 years ago)
• Last Synced: 2025-03-05T17:25:09.409Z (over 1 year ago)
• Topics: artificial-intelligence, deep-learning, machine-learning, multi-layer-perceptron, numpy, personal
• Language: Python
• Homepage:
• Size: 1.16 MB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# NeuralNetworkFromScratch

## Table of contents :

1. [Presentation](#presentation-)

3. [How to use](#how-to-use-)

2. [How does it work](#how-does-it-work-)

4. [Links](#links-)

## Presentation



>After coding a really simple perceptron, I wanted to build a multi-layer neural network from scratch using only numpy. I'm also currently reading the [nnfs](https://nnfs.io) book. I'm trying to go really slow on this project so I can learn and memorize all the informations. I'm reading a maximum of 2 chapters per session while making sure I understand each line of code and their theoretical context. I'm also writing a PDF file where you can find the mathematics behind that neural network, you can find it at the root of the repository.

## Book's chapters 

Chapter 1 - Introducing Neural Networks


Chapter 2 - Coding Our First Neurons


Chapter 3 - Adding Layers


Chapter 4 - Activation Functions


Chapter 5 - Loss


Chapter 6 - Optimization


Chapter 7 - Derivatives


Chapter 8 - Gradients, Partial Derivatives, and the Chain Rule


Chapter 9 - Backpropagation


Chapter 10 - Optimizers <---------------------------------------------------------- HERE ATM


Chapter 11 - Testing Data


Chapter 12 - Validation Data


Chapter 13 - Training Dataset


Chapter 14 - L1 and L2 Regularization


Chapter 15 - Dropout


Chapter 16 - Binary Logistic Regression


Chapter 17 - Regression


Chapter 18 - Model Object


Chapter 19 - A Real Dataset


Chapter 20 - Model Evaluation


Chapter 21 - Saving and Loading Model Information


Chapter 22 - Model Predicting/Inference

## How to use

>I'm currently thinking about interesting examples. Currently I'm testing it on different 2D vertical/spiral data plots.

## How does it work

>You can check the links below if you want further informations.

 

## Links

- https://nnfs.io

- https://nnfs.io/neural_network_animations

- https://en.wikipedia.org/wiki/Neural_network

- https://www.youtube.com/user/sentdex

- https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi

- https://machinelearning.wtf/acronyms/