Skip to content

vkrd/Neural-Network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Network From Scratch

Hi! I am a computer science student and this repository is where I am keeping my neural network I am building from scratch! I am doing this project to gain a deeper (pun intended) understanding of neural networks.

Setup

The only libraries you need to have are listed below with their pip installations. Numpy is used for linear algebra and tqdm is used to monitor training progress.

pip install numpy
pip install tqdm

Features

General

  • Multiple hidden layers
  • Backpropagation
  • Multiple activation functions
  • Learning rate scheduler
  • High level network builder
  • Save/Load model architecture and weights (customized file formats)
  • Regularization
  • Test/Train split

Layers

  • Dense
  • Dropout
  • Memory
  • Recurrent

Optimizers

  • Gradient Descent
  • Momentum
  • Stochastic Gradient Descent
  • Nesterov Accelerated Gradient
  • RMSProp
  • Adam

References

A Step by Step Backpropagation Example

Learning Rate Schedules

Overview of different Optimizers for neural networks

About

A neural network engine built using numpy

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages