Sciweavers

74 search results - page 1 / 15
» A New Approach to Knowledge-Based Design of Recurrent Neural...
Sort
View
TNN
2008
88views more  TNN 2008»
13 years 4 months ago
A New Approach to Knowledge-Based Design of Recurrent Neural Networks
Abstract-- A major drawback of artificial neural networks (ANNs) is their black-box character. This is especially true for recurrent neural networks (RNNs) because of their intrica...
Eyal Kolman, Michael Margaliot
ICANN
2010
Springer
13 years 5 months ago
Designing Simple Nonlinear Filters Using Hysteresis of Single Recurrent Neurons for Acoustic Signal Recognition in Robots
Abstract. In this article we exploit the discrete-time dynamics of a single neuron with self-connection to systematically design simple signal filters. Due to hysteresis effects an...
Poramate Manoonpong, Frank Pasemann, Christoph Kol...
IJCNN
2007
IEEE
13 years 11 months ago
Toyota Prius HEV neurocontrol
A neural network controller for improved fuel efficiency of the Toyota Prius hybrid electric vehicle is proposed. A new method to detect and mitigate a battery fault is also pres...
Danil V. Prokhorov
GECCO
2005
Springer
196views Optimization» more  GECCO 2005»
13 years 10 months ago
Breeding swarms: a new approach to recurrent neural network training
This paper shows that a novel hybrid algorithm, Breeding Swarms, performs equal to, or better than, Genetic Algorithms and Particle Swarm Optimizers when training recurrent neural...
Matthew Settles, Paul Nathan, Terence Soule