https://github.com/dhruvsrikanth/pynn

Purely NumPy based API for building deep neural networks.
https://github.com/dhruvsrikanth/pynn

deep-learning deep-learning-framework machine-learning numpy python pytorch

Last synced: 24 days ago
JSON representation

Purely NumPy based API for building deep neural networks.

• Host: GitHub
• URL: https://github.com/dhruvsrikanth/pynn
• Owner: DhruvSrikanth
• License: mit
• Created: 2022-07-25T03:51:16.000Z (almost 4 years ago)
• Default Branch: master
• Last Pushed: 2022-08-27T22:14:11.000Z (almost 4 years ago)
• Last Synced: 2025-04-23T22:13:53.539Z (about 1 year ago)
• Topics: deep-learning, deep-learning-framework, machine-learning, numpy, python, pytorch
• Language: Python
• Homepage:
• Size: 2.66 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# PyNN

A pure `numpy` implementation of `layers`, `learning algorithms` and `objective functions` for `neural networks`.



    

    

    

    



## Layers and Activation Functions

Layers:

1. Linear

2. Convolution (in-progress)

Activation Functions:

1. Sigmoid

2. Softmax

3. ReLU

4. Tanh (in-progress)

5. LeakyReLU

## Learning Algorithms

1. Stochastic Mini-Batch Gradient Descent

## Metrics

1. Area Under the Curve (AUC)

## Objective Functions

1. Mean Squared Error

2. Categorical Cross Entropy