Sciweavers

869 search results - page 13 / 174
» An Effective Learning Method for Max-Min Neural Networks
Sort
View
103
Voted
NN
2002
Springer
113views Neural Networks» more  NN 2002»
14 years 11 months ago
Control of exploitation-exploration meta-parameter in reinforcement learning
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
Shin Ishii, Wako Yoshida, Junichiro Yoshimoto
IPC
2007
IEEE
15 years 6 months ago
Mining User Models for Effective Adaptation of Context-Aware Applications
Current context-aware adaptation techniques are limited in their support for user personalisation. Complex codebases, a reliance on developer modification and an inability to auto...
Shiu Lun Tsang, Siobhán Clarke
AIPRF
2007
15 years 1 months ago
Instinct and Learning Synergy in Simulated Foraging Using a Neural Network
Instinct and experience are shown to form a potent combination to achieve effective foraging in a simulated environment. A neural network capable of evolving instinct-related neur...
Thomas E. Portegys
IJCNN
2006
IEEE
15 years 5 months ago
Learning using Dynamical Regime Identification and Synchronization
—This study proposes to generalize Hebbian learning by identifying and synchronizing the dynamical regimes of individual nodes in a recurrent network. The connection weights are ...
Nicolas Brodu
BMCBI
2010
174views more  BMCBI 2010»
14 years 11 months ago
The effect of prior assumptions over the weights in BayesPI with application to study protein-DNA interactions from ChIP-based h
Background: To further understand the implementation of hyperparameters re-estimation technique in Bayesian hierarchical model, we added two more prior assumptions over the weight...
Junbai Wang