Sciweavers

498 search results - page 40 / 100
» Training Neural Networks with GA Hybrid Algorithms
Sort
View
ISCAS
2007
IEEE
122views Hardware» more  ISCAS 2007»
15 years 8 months ago
Neuromimetic ICs with analog cores: an alternative for simulating spiking neural networks
- This paper aims at discussing the implementation of simulation systems for SNN based on analog computation cores (neuromimetic ICs). Such systems are an alternative to completely...
Sylvie Renaud, Jean Tomas, Yannick Bornat, Adel Da...
CIG
2006
IEEE
15 years 3 months ago
Improving Artificial Intelligence In a Motocross Game
We have previously investigated the use of artificial neural networks to ride simulated motorbikes in a new computer game. These artificial neural networks were trained using two d...
Benoit Chaperot, Colin Fyfe
ICONIP
2009
14 years 11 months ago
"Dead" Chromosomes and Their Elimination in the Neuro-Genetic Stock Index Prediction System
This paper presents a method for a short-term stock index prediction. The source data comes from the German Stock Exchange (being the target market) and two other markets (Tokyo St...
Jacek Mandziuk, Marcin Jaruszewicz
FUZZY
1997
Springer
260views Fuzzy Logic» more  FUZZY 1997»
15 years 6 months ago
Forecasting Sales Using Neural Networks
Abstract. In this paper, neural networks trained with the back-propagation algorithm are applied to predict the future values of time series that consist of the weekly demand on it...
Frank M. Thiesing, Oliver Vornberger
ICANN
2010
Springer
15 years 2 months ago
Computational Properties of Probabilistic Neural Networks
We discuss the problem of overfitting of probabilistic neural networks in the framework of statistical pattern recognition. The probabilistic approach to neural networks provides a...
Jiri Grim, Jan Hora