https://github.com/dadadel/multilayerperceptron
Multi Layer Perceptron
https://github.com/dadadel/multilayerperceptron
multilayer-perceptron neural-network numpy python3
Last synced: 6 months ago
JSON representation
Multi Layer Perceptron
- Host: GitHub
- URL: https://github.com/dadadel/multilayerperceptron
- Owner: dadadel
- Created: 2018-01-25T13:11:08.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2018-01-25T13:11:48.000Z (over 7 years ago)
- Last Synced: 2025-02-01T19:44:22.078Z (8 months ago)
- Topics: multilayer-perceptron, neural-network, numpy, python3
- Language: Jupyter Notebook
- Homepage:
- Size: 229 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Multi-Layer Perceptron
This is a Python 3 implementation of a multi-layer perceptron using Numpy and optionally Matplotlib for cost function visualization.
It is provided under GPLv3 licence.
It implements forward-propagation and backward-propagation (gradient descent).
It allows to learn examples and trying to minimize cost function.
It provides also Momentum optimization, RMSProp optimization, Adam optimization and Forbenius norm regularization.
Note: I developed this only to implement myself the algorithms for fun and not for any production purpose. I already coded MLPs years ago in C and in C++.
I tested it with images of characters (in PGM format) extracted from a scanned image with an other program I developed many years ago in C++ but very dirty so I don't provide it.
I provide the jupyter notebook I used for some tests.