Thread Subject: Neural Network multiple outputs training

Subject: Neural Network multiple outputs training

From: sanepa

Date: 15 Apr, 2003 12:33:17

Message: 1 of 2

Hello everybody,


The backpropagation algorithm seems to train the ANNs only for the
output at the last layer. Is it possible to train the network for the
multiple outputs from different layers?

Subject: Neural Network multiple outputs training

From: heath@ll.mit.edu (Greg Heath)

Date: 16 Apr, 2003 09:38:21

Message: 2 of 2

sanepa <sanepa@web.de> wrote in message
news:<eebc828.-1@WebX.raydaftYaTP>...

> The backpropagation algorithm seems to train the ANNs only for the
> output at the last layer. Is it possible to train the network for the
> multiple outputs from different layers?

I guess you could do it. But I can't think of a good reason
why anyone would want to do it.

Please explain.

Hope this helps.

Tags for this Thread

Add a New Tag:

Separated by commas
Ex.: root locus, bode

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

rssFeed for this Thread

Contact us at files@mathworks.com