Re: Please help in Neural Network Implementaion !!


Subject: Re: Please help in Neural Network Implementaion !!
From: Myriam Othmane (myriam.othmane@wanadoo.be)
Date: Tue Feb 15 2000 - 21:22:10 MET


In your book : Numerical Recipes in C (or in Pascal), you will find the
programming technics (gradient descent, newton gauss, calculate the Hessian
Matrix, ...).
I' ve never programming these technics (I use built-in sotfware).
I think that you can find code directly on the internet or buy some book.
By example :

Neural Networks Programming in C++: An Object-Oriented Framework for
Building Connectionist Systems
Abstract: Focuses on the practical side of building neural networks, using
C++. Includes diskette.
Keywords: book review, robotics, ai, programming, object-oriented, C++
computer program language, connectionist, neural nets, neural networks,
science.

Title: Neural Networks Programming in C++: An Object-Oriented Framework for
Building Connectionist Systems
Author: Adam Blum
Publisher: John Wiley
Date Published: November 1991
ISBN: 0471538477
LOCN: QA76.87.B58 1992
Dewey: 006.3 20
Pages: 213
Bibliography: 37 entries

Have fun and stay in touch,
Manuel.

Joe Smith <jsmith@currentreviews.com> a écrit dans le message :
38A1F63E.32897D35@currentreviews.com...
> Dear Manuel,
>
> Do you have sample code that you can share with us. I'm a programmer
> not a mathematician and It would be a lot easier to understand the
> concept from the code.
>
>
>
>
> Thank you,
>
> Joe Smith
> jsmith@currentreviews.com
>
>
> Myriam Othmane wrote:
> >
> > Hello,
> > I am not a expert in RBF, but I think RBF is more robust to outliers
> > (apologize for my english writting). The MLP will not generalize well
with
> > this data (he goes in saturation) and the average error of the
validation
> > set will become very instable. With the RBF and the locally
(multivariate
> > gaussian distribution) , the effect of a 'outlier' (extreme value) will
> > vanish more easily.
> > Indeed, I think the outliers will increase the variance (spread,
smoothing
> > parameter) but they will have less impact on the convergence of the
> > algorithm.
> > I have just experienced this result from very skew distribution (with a
lot
> > of extremes values), may be it was a artefact of my data.
> > If you can give me insight, I will be glad.
> > Thank's
> > Manuel.
> >

############################################################################
This message was posted through the fuzzy mailing list.
(1) To subscribe to this mailing list, send a message body of
"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
(2) To unsubscribe from this mailing list, send a message body of
"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
to listproc@dbai.tuwien.ac.at
(3) To reach the human who maintains the list, send mail to
fuzzy-owner@dbai.tuwien.ac.at
(4) WWW access and other information on Fuzzy Sets and Logic see
http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html



This archive was generated by hypermail 2b25 : Thu Apr 06 2000 - 15:59:44 MET DST