Sciweavers

298 search results - page 35 / 60
» Optimizing number of hidden neurons in neural networks
Sort
View
IWANN
2009
Springer
14 years 2 months ago
A Genetic Algorithm for ANN Design, Training and Simplification
This paper proposes a new evolutionary method for generating ANNs. In this method, a simple real-number string is used to codify both architecture and weights of the networks. Ther...
Daniel Rivero, Julian Dorado, Enrique Ferná...
DMSN
2008
ACM
13 years 9 months ago
Probabilistic processing of interval-valued sensor data
When dealing with sensors with different time resolutions, it is desirable to model a sensor reading as pertaining to a time interval rather than a unit of time. We introduce two ...
Sander Evers, Maarten M. Fokkinga, Peter M. G. Ape...
IEAAIE
1998
Springer
14 years 3 days ago
Complexity and Cognitive Computing
Abstract. This paper has as main goal to develop a hybrid expert system to minimize some of the complexity problems related to arti cial intelligence eld. For instance, we can ment...
Lourdes Mattos Brasil, Fernando Mendes de Azevedo,...
NN
2007
Springer
14 years 2 months ago
Impact of Higher-Order Correlations on Coincidence Distributions of Massively Parallel Data
The signature of neuronal assemblies is the higher-order correlation structure of the spiking activity of the participating neurons. Due to the rapid progress in recording technol...
Sonja Grün, Moshe Abeles, Markus Diesmann
FOCI
2007
IEEE
14 years 2 months ago
Almost All Learning Machines are Singular
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Sumio Watanabe