Sciweavers

2295 search results - page 28 / 459
» Learning Overcomplete Representations
Sort
View
FLAIRS
2003
13 years 10 months ago
Improving the Representation Space through Exception-Based Learning
This paper addresses the problem of improving the representation space in a rule-based intelligent system, through exception-based learning. Such a system generally learns rules c...
Cristina Boicu, Gheorghe Tecuci, Mihai Boicu, Dori...
ICML
2008
IEEE
14 years 9 months ago
An object-oriented representation for efficient reinforcement learning
Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces. We introduce Object...
Carlos Diuk, Andre Cohen, Michael L. Littman
AIED
2009
Springer
14 years 3 months ago
Transfer Learning and Representation Discovery in Intelligent Tutoring Systems
We describe a novel framework developed for transfer learning within reinforcement learning (RL) problems. Then we exhibit how this framework can be extended to intelligent tutorin...
Kimberly Ferguson, Beverly Park Woolf, Sridhar Mah...
AAAI
2004
13 years 10 months ago
Distributed Representation of Syntactic Structure by Tensor Product Representation and Non-Linear Compression
Representing lexicons and sentences with the subsymbolic approach (using techniques such as Self Organizing Map (SOM) or Artificial Neural Network (ANN)) is a relatively new but i...
Heidi H. T. Yeung, Peter W. M. Tsang
PAMI
2012
11 years 11 months ago
Task-Driven Dictionary Learning
—Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience, and signal proce...
Julien Mairal, Francis Bach, Jean Ponce