Sciweavers

4930 search results - page 389 / 986
» Learning minimal abstractions
Sort
View
ICML
2010
IEEE
15 years 8 months ago
Internal Rewards Mitigate Agent Boundedness
Abstract--Reinforcement learning (RL) research typically develops algorithms for helping an RL agent best achieve its goals-however they came to be defined--while ignoring the rela...
Jonathan Sorg, Satinder P. Singh, Richard Lewis
ML
2008
ACM
146views Machine Learning» more  ML 2008»
15 years 6 months ago
Improving maximum margin matrix factorization
Abstract. Collaborative filtering is a popular method for personalizing product recommendations. Maximum Margin Matrix Factorization (MMMF) has been proposed as one successful lear...
Markus Weimer, Alexandros Karatzoglou, Alex J. Smo...
158
Voted
TSMC
2002
98views more  TSMC 2002»
15 years 6 months ago
The STAR automaton: expediency and optimality properties
Abstract--We present the STack ARchitecture (STAR) automaton. It is a fixed structure, multiaction, reward-penalty learning automaton, characterized by a star-shaped state transiti...
Anastasios A. Economides, Athanasios Kehagias
173
Voted
ICONIP
2010
15 years 5 months ago
Improving Recurrent Neural Network Performance Using Transfer Entropy
Abstract. Reservoir computing approaches have been successfully applied to a variety of tasks. An inherent problem of these approaches, is, however, their variation in performance ...
Oliver Obst, Joschka Boedecker, Minoru Asada
ML
2010
ACM
181views Machine Learning» more  ML 2010»
15 years 5 months ago
Decomposing the tensor kernel support vector machine for neuroscience data with structured labels
Abstract The tensor kernel has been used across the machine learning literature for a number of purposes and applications, due to its ability to incorporate samples from multiple s...
David R. Hardoon, John Shawe-Taylor