https://github.com/ostad-ai/backpropagation

Here, Backpropagaation algorithm is implemented with pure Python, only with Python standard library.
https://github.com/ostad-ai/backpropagation

backpropagation classification gradient-descent iris neural-networks opensource pure python

Last synced: about 1 month ago
JSON representation

Here, Backpropagaation algorithm is implemented with pure Python, only with Python standard library.

• Host: GitHub
• URL: https://github.com/ostad-ai/backpropagation
• Owner: ostad-ai
• License: mit
• Created: 2024-08-10T15:14:44.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-08-10T18:10:47.000Z (4 months ago)
• Last Synced: 2024-08-10T19:40:55.247Z (4 months ago)
• Topics: backpropagation, classification, gradient-descent, iris, neural-networks, opensource, pure, python
• Language: Python
• Homepage:
• Size: 4.88 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Backpropagation, pure Python, version 0.0

1. Backpropagation with pure Python. 

- Here, we use no external library to implement a Backpropagation algorithm for a three-layer MLP (Multilayer Perceptron).

2. To use the available code for backpropagation, at the top of your code, write: from bp_pure import *

3. Remember to download **bp_pure.py**.

4. This implementation uses biases for both input and hidden layers.

5. For now, only an online training for backpropagation has been implemented.

6. As an example, download and use **bp_pure_example.ipynb** and **iris.csv** to test the backpropagation algorithm.