Skip to content

Latest commit

 

History

History
23 lines (14 loc) · 1 KB

README.md

File metadata and controls

23 lines (14 loc) · 1 KB
Raw

NPNetwork-v1.1

A Matlab class for no propagation adaptive neural network. This adaptive neural network model is developed by Prof. Bernard Widrow's research group at Stanford University, Stanford, CA, USA. This Matlab class is developed by Yizheng Liao, a PhD student at Stanford University.

Release Note for v1.1

correct following bug:

  1. correct the incorrect weights for fixed layer weights which are generated by Gaussian distribution

add following feature:

  1. display parameters for Training function

lyz@March 14th, 2013

Release Note for v1.0

In v1.0, we implemented the following features:

  1. Training the neural network with only LMS adaptive layers. This feature can be used to model the linear system.
  2. Training the neural network with hidden layers and LMS adaptive layers. This feature can be used to model the non linear system with or without sigmoid function at plant output.

If you have any question, please feel free to contact Yizheng (yzliao at stanford dot edu).

lyz@March 6th, 2013