Sciweavers

257 search results - page 41 / 52
» neco 2006
Sort
View
NECO
2002
105views more  NECO 2002»
13 years 7 months ago
Multiple Model-Based Reinforcement Learning
We propose a modular reinforcement learning architecture for non-linear, nonstationary control tasks, which we call multiple model-based reinforcement learning (MMRL). The basic i...
Kenji Doya, Kazuyuki Samejima, Ken-ichi Katagiri, ...
NECO
2007
107views more  NECO 2007»
13 years 7 months ago
Training a Support Vector Machine in the Primal
Most literature on Support Vector Machines (SVMs) concentrate on the dual optimization problem. In this paper, we would like to point out that the primal problem can also be solve...
Olivier Chapelle
NECO
2007
70views more  NECO 2007»
13 years 7 months ago
Solution Methods for a New Class of Simple Model Neurons
Recently Izhikevich (2003) proposed a new canonical neuron model of spike generation. The model was surprisingly simple, yet able to accurately replicate the firing patterns of d...
Mark D. Humphries, Kevin N. Gurney
NECO
2010
92views more  NECO 2010»
13 years 6 months ago
Roles of Inhibitory Neurons in Rewiring-Induced Synchronization in Pulse-Coupled Neural Networks
The roles of inhibitory neurons in synchronous firing are examined in a network of excitatory and inhibitory neurons with Watts and Strogatz’s rewiring. By examining the persis...
Takashi Kanamaru, Kazuyuki Aihara
NECO
2006
118views more  NECO 2006»
13 years 7 months ago
Consistency of Pseudolikelihood Estimation of Fully Visible Boltzmann Machines
Boltzmann machine is a classic model of neural computation, and a number of methods have been proposed for its estimation. Most methods are plagued by either very slow convergence...
Aapo Hyvärinen