22 search results - page 4 / 5 » Scalable Architecture for on-Chip Neural Network Training us... |
CEC
2009
IEEE
14 years 8 days ago
2009
IEEE
Abstract— In this paper we describe simulation of autonomous robots controlled by recurrent neural networks, which are evolved through indirect encoding using HyperNEAT algorithm...
IJCNN
2008
IEEE
13 years 12 months ago
2008
IEEE
Abstract— Automatic pattern classifiers that allow for incremental learning can adapt internal class models efficiently in response to new information, without having to retrai...
ECAI
2010
Springer
13 years 6 months ago
2010
Springer
Abstract. Deep Neural Networks (DNN) propose a new and efficient ML architecture based on the layer-wise building of several representation layers. A critical issue for DNNs remain...
IJCNN
2008
IEEE
13 years 12 months ago
2008
IEEE
— Numerical condition affects the learning speed and accuracy of most artificial neural network learning algorithms. In this paper, we examine the influence of opposite transfe...
MICAI
2004
Springer
13 years 11 months ago
2004
Springer
Abstract. Conventional artificial neural network models lack many physiological properties of the neuron. Current learning algorithms are more concerned to computational performanc...