Sciweavers

909 search results - page 101 / 182
» Introduction to artificial neural networks
Sort
View
EVOW
2008
Springer
13 years 9 months ago
Implicit Fitness Functions for Evolving a Drawing Robot
We describe an approach to artificially evolving a drawing robot using implicit fitness functions, which are designed to minimise any direct reference to the line patterns made by ...
Jon Bird, Phil Husbands, Martin Perris, Bill Bigge...
PRL
2008
81views more  PRL 2008»
13 years 8 months ago
Selecting and constructing features using grammatical evolution
A novel method for feature selection and construction is introduced. The method improves the classification accuracy, utilizing the well-established technique of grammatical evolu...
Dimitris Gavrilis, Ioannis G. Tsoulos, Evangelos D...
IJCNN
2006
IEEE
14 years 2 months ago
In Situ Training of CMOL CrossNets
—— Hybrid semiconductor/nanodevice (“CMOL”) technology may allow the implementation of digital and mixed-signal integrated circuits, including artificial neural networks (...
Jung Hoon Lee, Konstantin Likharev
GECCO
2007
Springer
212views Optimization» more  GECCO 2007»
14 years 2 months ago
A developmental model of neural computation using cartesian genetic programming
The brain has long been seen as a powerful analogy from which novel computational techniques could be devised. However, most artificial neural network approaches have ignored the...
Gul Muhammad Khan, Julian F. Miller, David M. Hall...
NIPS
2001
13 years 9 months ago
(Not) Bounding the True Error
We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifier...
John Langford, Rich Caruana