4080 search results - page 493 / 816 » The rebirth of neural networks |
206
click to vote
ICANN
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. Trained support vector machines (SVMs) have a slow runtime classification speed if the classification problem is noisy and the sample data set is large. Approximating the...
184
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 ...
184
click to vote
ICANN
2007
Springer
15 years 10 months ago
2007
Springer
Meta-Learning has been used to select algorithms based on the features of the problems being tackled. Each training example in this context, i.e. each meta-example, stores the feat...
173
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...
184
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...