Sciweavers

17 search results - page 3 / 4
» Global Optimization Algorithms for Training Product Unit Neu...
Sort
View
CEC
2007
IEEE
14 years 1 months ago
Improving generalization capability of neural networks based on simulated annealing
— This paper presents a single-objective and a multiobjective stochastic optimization algorithms for global training of neural networks based on simulated annealing. The algorith...
Yeejin Lee, Jong-Seok Lee, Sun-Young Lee, Cheol Ho...
SBRN
2000
IEEE
13 years 12 months ago
Adaptation of Parameters of BP Algorithm Using Learning Automata
d Articles >> Table of Contents >> Abstract VI Brazilian Symposium on Neural Networks (SBRN'00) p. 24 Adaptation of Parameters of BP Algorithm Using Automata Hamid...
Hamid Beigy, Mohammad Reza Meybodi
ESWA
2006
154views more  ESWA 2006»
13 years 7 months ago
Artificial neural networks with evolutionary instance selection for financial forecasting
In this paper, I propose a genetic algorithm (GA) approach to instance selection in artificial neural networks (ANNs) for financial data mining. ANN has preeminent learning abilit...
Kyoung-jae Kim
ECML
2007
Springer
14 years 1 months ago
Nondeterministic Discretization of Weights Improves Accuracy of Neural Networks
Abstract. The paper investigates modification of backpropagation algorithm, consisting of discretization of neural network weights after each training cycle. This modification, a...
Marcin Wojnarski
IJCNN
2008
IEEE
14 years 1 months ago
Two-level clustering approach to training data instance selection: A case study for the steel industry
— Nowadays, huge amounts of information from different industrial processes are stored into databases and companies can improve their production efficiency by mining some new kn...
Heli Koskimäki, Ilmari Juutilainen, Perttu La...