1173 search results - page 143 / 235 » Neural networks for computational neuroscience |
179
click to vote
ICANN
2007
Springer
15 years 10 months ago
2007
Springer
It is well known that our prior knowledge and experiences affect how we learn new concepts. Although several formal modeling attempts have been made to quantitatively describe the ...
163
click to vote
ICANN
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. In this paper we present a novel method for pruning redundant weights of a trained multilayer Perceptron (MLP). The proposed method is based on the correlation analysis o...
177
click to vote
ICANN
2009
Springer
15 years 10 months ago
2009
Springer
In a typical reinforcement learning (RL) setting details of the environment are not given explicitly but have to be estimated from observations. Most RL approaches only optimize th...
186
click to vote
ANNPR
2006
Springer
15 years 10 months ago
2006
Springer
Abstract. In our previous work we have shown that Mahalanobis kernels are useful for support vector classifiers both from generalization ability and model selection speed. In this ...
174
click to vote
ANNPR
2006
Springer
15 years 10 months ago
2006
Springer
We discuss incremental training of support vector machines in which we approximate the regions, where support vector candidates exist, by truncated hypercones. We generate the trun...