8381 search results - page 1326 / 1677 » The security of machine learning |
194
click to vote
IJCNN
2006
IEEE
16 years 24 days ago
2006
IEEE
Abstract— While the model parameters of many kernel learning methods are given by the solution of a convex optimisation problem, the selection of good values for the kernel and r...
215
click to vote
IJCNN
2006
IEEE
16 years 24 days ago
2006
IEEE
— A solution for the slow convergence of most learning rules for Recurrent Neural Networks (RNN) has been proposed under the terms Liquid State Machines (LSM) and Echo State Netw...
191
click to vote
ACOM
2006
Springer
16 years 23 days ago
2006
Springer
Communication in multi-agent systems (MASs) is usually governed by agent communication languages (ACLs) and communication protocols carrying a clear cut semantics. With an increasi...
196
click to vote
SIGECOM
2006
ACM
16 years 21 days ago
2006
ACM
We present a reduction from graphical games to Markov random fields so that pure Nash equilibria in the former can be found by statistical inference on the latter. Our result, wh...
183
click to vote
CIG
2005
IEEE
16 years 11 days ago
2005
IEEE
The aim of developing an agent that is able to adapt its actions in response to their effectiveness within the game provides the basis for the research presented in this paper. It ...