Neural Nets written in LabVIEW !

[BetaCommunityCo]

Overview

This example provides a functional and clean Neural Net program for all to use as long as the author gets credit. Enjoy.

Description

This VI simulates a basic learning process through a Backpropagation Artificial Neural Network Model. This is a supervised model in which there are two input values sent to an input layer, the weight matrix passes to a hidden layer through a second weight matrix to the output layer. The chart shows the error vs repetitions of the input.

Steps to Implement or Execute Code

1. Download the NeuraNet Example Zip file
2. Unzip the file in a desired location
3. Run the NN Example.vi for a quick working example to show the outcome
4. More information is included in the Zip file within the project and also the txt file
5. For more information about the topic, go to the link within the comments section of this page

Requirements to Run

Software

 LabVIEW Base Development System 2012 or compatible

Additional Images

Front Panel

Block Diagram

-Chuck Streb

chuck.streb@gmail.com

**This document has been updated to meet the current required format for the NI Code Exchange. **

[BetaCommunityCo]

Is there an explanation or documentation?

This appears to be an interesting example, however I am having a great deal of trouble following it as there's no documentation or comments. In looking at the code, I'd guess that everything makes perfect sense to those intimately familiar with neural nets (I read up on them some years back so I am certainly not intimate). Would it be possible to add documentation or point people to a resource?

[carlfield]

very goog code of ANN written by LabVIEW,although just BP ANN.

thank U very much!

[ChuckS]

here is some info

http://fbim.fh-regensburg.de/~saj39122/jfroehl/diplom/e-13-text.html

[Yodo2]

Check out also this one:

http://sine.ni.com/cs/app/doc/p/id/cs-681

Email me if you want to get the code: stan.zurek@ieee.org

Stan

[jincena]

we have already done learning for bpn but do u have any idea on how to use this net for prediction

[ChuckS]

You need to unitize/scale (0to1) your inputs into this net and then convert back after.

Sorry I didn’t make a better example

[PrimaryKey]

Hi All, there is a very easy to use version of neural nets toolkit available for testing if you need.

https://decibel.ni.com/content/docs/DOC-41891

[ChuckS]

current link for information

https://www.nnwj.de/backpropagation.html