Welcome to Scribd, the world's digital library. Read, publish, and share books and documents. See more
Download
Standard view
Full view
of .
Look up keyword
Like this
1Activity
0 of .
Results for:
No results containing your search query
P. 1
Flood 2 Users Guide

Flood 2 Users Guide

Ratings: (0)|Views: 67|Likes:
Published by tonehog457011792
Flood 2
An Open Source Neural Networks C++ Library. www.cimne.com/flood User’s Guide.
Roberto Lopez International Center for Numerical Methods in Engineering (CIMNE) Technical University of Catalonia (UPC) Barcelona, Spain E-mail: rlopez@cimne.upc.edu December 2008

Preface
The multilayer perceptron is an important model of neural network, and much of the literature in the field is referred to that model. The multilayer perceptron has found a wide range of applications, which include function reg
Flood 2
An Open Source Neural Networks C++ Library. www.cimne.com/flood User’s Guide.
Roberto Lopez International Center for Numerical Methods in Engineering (CIMNE) Technical University of Catalonia (UPC) Barcelona, Spain E-mail: rlopez@cimne.upc.edu December 2008

Preface
The multilayer perceptron is an important model of neural network, and much of the literature in the field is referred to that model. The multilayer perceptron has found a wide range of applications, which include function reg

More info:

Published by: tonehog457011792 on Feb 13, 2010
Copyright:Attribution Non-commercial

Availability:

Read on Scribd mobile: iPhone, iPad and Android.
download as PDF, TXT or read online from Scribd
See more
See less

02/12/2010

pdf

text

original

 
Flood 2
An Open Source Neural Networks C++ Library.www.cimne.com/floodUser’s Guide.
Roberto LopezInternational Center for Numerical Methods in Engineering (CIMNE)Technical University of Catalonia (UPC)Barcelona, SpainE-mail: rlopez@cimne.upc.eduDecember 2008
 
Preface
The multilayer perceptron is an important model of neural network, and much of theliterature in the field is referred to that model. The multilayer perceptron has founda wide range of applications, which include function regression, pattern recognition,time series prediction, optimal control, inverse problems or optimal shape design. Allthese problems can be formulated as variational problems.
Flood
is a comprehensive class library which implements the multilayer perceptronin the C++ programming language. It has been developed following the functionalanalysis and calculus of variations theories. In this regard, this software tool canbe used for the whole range of applications mentioned above.
Flood
also provides aworkaround for the solution of function optimization problems. The library has beenreleased as the open source GNU Lesser General Public License.i
 
Contents
namespace. . . . . . . . . . . . . . . . . . . . . . . . . . . . 21.2 The Vector and Matrix classes in
. . . . . . . . . . . . . . . . . . 2
3.1 The elements of the perceptron. . . . . . . . . . . . . . . . . . . . . . . 63.2 The perceptron function space. . . . . . . . . . . . . . . . . . . . . . . 103.3 The Perceptron class in Flood. . . . . . . . . . . . . . . . . . . . . . . . 11
4.1 Feed-forward architectures. . . . . . . . . . . . . . . . . . . . . . . . . . 134.2 The multilayer perceptron function space. . . . . . . . . . . . . . . . . 144.3 The Jacobian matrix. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 164.4 Universal approximation. . . . . . . . . . . . . . . . . . . . . . . . . . . 194.5 Pre and post-processing. . . . . . . . . . . . . . . . . . . . . . . . . . . 194.6 Multilayer perceptron extensions. . . . . . . . . . . . . . . . . . . . . . 204.7 The input-output activity diagram. . . . . . . . . . . . . . . . . . . . . 224.8 The MultilayerPerceptron class in Flood. . . . . . . . . . . . . . . . . . 22
5.1 The variational problem. . . . . . . . . . . . . . . . . . . . . . . . . . . 275.2 The reduced function optimization problem. . . . . . . . . . . . . . . . 295.3 The objective function gradient. . . . . . . . . . . . . . . . . . . . . . . 305.4 The objective function Hessian. . . . . . . . . . . . . . . . . . . . . . . 355.5 The ObjectiveFunctional classes in Flood. . . . . . . . . . . . . . . . . 36
6.1 The function optimization problem. . . . . . . . . . . . . . . . . . . . . 386.2 Random search. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 406.3 Gradient descent. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 416.4 Newton’s method. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 416.5 Conjugate gradient. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 446.6 Quasi-Newton method. . . . . . . . . . . . . . . . . . . . . . . . . . . . 456.7 One-dimensional minimization algorithms. . . . . . . . . . . . . . . . . 476.8 Evolutionary algorithm. . . . . . . . . . . . . . . . . . . . . . . . . . . 486.9 The TrainingAlgorithm classes in Flood. . . . . . . . . . . . . . . . . . 53ii

You're Reading a Free Preview

Download
scribd
/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->