🌐 AI搜索 & 代理 主页
Skip to content

Python implementation of feed-forward multi-layer perceptron neural network using only numpy and scipy

Notifications You must be signed in to change notification settings

basicmachines/mlp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 

Repository files navigation

mlpnet.py

Python implementation of feed-forward multi-layer perceptron (MLP) neural networks using numpy and scipy based on theory taught by Andrew Ng on coursera.org and adapted from the Octave code examples from this course as well as updates from the 2017 deeplearning.ai Deep Learning Specialization course..

This is still a work-in-progress. Still some bugs and fixes to do so don't recommend using this yet...

Applications

  • Classification
  • Prediction
  • Model Predictive Control (MPC)
  • Approximation of non-linear functions

Main Classes

  • MLPLayer - Multi-layer perceptron neural network layer class (used by MLPNetwork)
  • MLPNetwork - Multi-layer perceptron neural network class
  • MLPTrainingData - Object to store training data (inputs and outputs).

Other Functions

  • train - Used to handle training of a network.

About

Python implementation of feed-forward multi-layer perceptron neural network using only numpy and scipy

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published