Thread Subject: neural networks generalisation

Subject: neural networks generalisation

From: cathrine lab

Date: 22 Mar, 2010 11:01:04

Message: 1 of 2

Dear all

I am working on characters recognition using neural networks
I have got good results (100 %) when testing the neural network on the same training data in the other case I got bad results (40 %)

I will be highly appreciated if any one help me about how to improve the neural network generalisation.
thanks in advance

Subject: neural networks generalisation

From: Maria_tab Manioudaki

Date: 22 Mar, 2010 11:46:04

Message: 2 of 2

"cathrine lab" <lousa_br@yahoo.fr> wrote in message <ho7ilg$8p6$1@fred.mathworks.com>...
> Dear all
>
> I am working on characters recognition using neural networks
> I have got good results (100 %) when testing the neural network on the same training data in the other case I got bad results (40 %)
>
> I will be highly appreciated if any one help me about how to improve the neural network generalisation.
> thanks in advance

How do you choose your training set
and what percentage of the test do you use for training?

Tags for this Thread

Everyone's Tags:

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.

Tag Activity for This Thread
Tag Applied By Date/Time
neural network ... cathrine lab 22 Mar, 2010 07:04:11
rssFeed for this Thread

Contact us at files@mathworks.com