748 search results - page 31 / 150 » A Reinforcement Learning Algorithm for Spiking Neural Networ... |
IJCNN
2006
IEEE
14 years 1 months ago
2006
IEEE
— Biped robots based on the concept of (passive) dynamic walking are far simpler than the traditional fullycontrolled walking robots, while achieving a more natural gait and cons...
NCA
2011
IEEE
13 years 2 months ago
2011
IEEE
—Neural Networks have been an active research area for decades. However, privacy bothers many when the training dataset for the neural networks is distributed between two parties...
ESANN
2003
13 years 8 months ago
2003
In this paper fully connected RTRL neural networks are studied. In order to learn dynamical behaviours of linear-processes or to predict time series, an autonomous learning algori...
ML
1998
ACM
13 years 7 months ago
1998
ACM
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
ATAL
2007
Springer
14 years 1 months ago
2007
Springer
The ambitious goal of transfer learning is to accelerate learning on a target task after training on a different, but related, source task. While many past transfer methods have f...