Sciweavers

1397 search results - page 147 / 280
» Dynamic power management using machine learning
Sort
View
EUROCAST
2007
Springer
182views Hardware» more  EUROCAST 2007»
15 years 9 months ago
A k-NN Based Perception Scheme for Reinforcement Learning
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
José Antonio Martin H., Javier de Lope Asia...
ICNC
2005
Springer
15 years 9 months ago
A Game-Theoretic Approach to Competitive Learning in Self-Organizing Maps
Abstract. Self-Organizing Maps (SOM) is a powerful tool for clustering and discovering patterns in data. Competitive learning in the SOM training process focusses on finding a neu...
Joseph P. Herbert, Jingtao Yao
128
Voted
NIPS
2003
15 years 5 months ago
Ambiguous Model Learning Made Unambiguous with 1/f Priors
What happens to the optimal interpretation of noisy data when there exists more than one equally plausible interpretation of the data? In a Bayesian model-learning framework the a...
Gurinder S. Atwal, William Bialek
IPPS
2002
IEEE
15 years 8 months ago
Utilization-Based Heuristics for Statically Mapping Real-Time Applications onto the HiPer-D Heterogeneous Computing System
Real-time applications continue to increase in importance as they are employed in various critical areas, such as command and control systems. These applications have traditionall...
Shoukat Ali, Jong-Kook Kim, Yang Yu, Shriram B. Gu...
AIIDE
2008
15 years 6 months ago
Talking with NPCs: Towards Dynamic Generation of Discourse Structures
Dialogue in commercial games is largely created by teams of writers and designers who hand-author every line of dialogue and hand-specify the dialogue structure using finite state...
Christina R. Strong, Michael Mateas