Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

7

KES
2007
Springer

favoriteEmaildiscussreport

106views Information Technology» more KES 2007»

Design of Neural Networks

13 years 10 months ago

Design of Neural Networks

Download lrb.cs.uni-dortmund.de

The paper offers a critical analysis of the procedure observed in many applications of neural networks. Given a problem to be solved, a favorite NN-architecture is chosen and its parameters tuned with some standard training algorithm, but without taking in consideration relevant features of the problem or possibly its interdisciplinary nature. Three relevant benchmark problems are discussed to illustrate the thesis that “brute force solving is not the same as understanding”. Keywords. Neural networks, pre-processing, problem-oriented design

Claudio Moraga

Real-time Traffic

Consideration Relevant Features | KES 2007 | Neural Networks | Relevant Benchmark Problems |

claim paper

Related Content

» A Methodology for ExampleBased Specification and Design

» The Cellular Simultaneous Recurrent Network Adaptive Critic Design for the Generalized Maz...

» Hardware Implementations of Artificial Neural Networks

» Adaptive Critic Design for Intelligent Steering and Speed Control of a 2Axle Vehicle

» Constructive Design of LVQ and DSM Classifiers

» NEURObjects an objectoriented library for neural network development

» Unsupervised Learning of Neural Network Ensembles for Image Classification

» Optimal design of hierarchical wavelet networks for timeseries forecasting

» A Descriptive Encoding Language for Evolving Modular Neural Networks

» The Architecture and Circuital Implementation Scheme of a New Cell Neural Network for Anal...

Post Info
More Details (n/a)

Added	08 Jun 2010
Updated	08 Jun 2010
Type	Conference
Year	2007
Where	KES
Authors	Claudio Moraga

Comments (0)