Sciweavers

15 search results - page 2 / 3
» Reasoning about Time and Knowledge in Neural Symbolic Learni...
Sort
View
IJCAI
2007
13 years 6 months ago
A Fully Connectionist Model Generator for Covered First-Order Logic Programs
We present a fully connectionist system for the learning of first-order logic programs and the generation of corresponding models: Given a program and a set of training examples,...
Sebastian Bader, Pascal Hitzler, Steffen Höll...
IJCAI
2007
13 years 6 months ago
Representations for Action Selection Learning from Real-Time Observation of Task Experts
The association of perception and action is key to learning by observation in general, and to programlevel task imitation in particular. The question is how to structure this info...
Mark A. Wood, Joanna Bryson
NIPS
2003
13 years 6 months ago
Learning a World Model and Planning with a Self-Organizing, Dynamic Neural System
We present a connectionist architecture that can learn a model of the relations between perceptions and actions and use this model for behavior planning. State representations are...
Marc Toussaint
CI
2005
106views more  CI 2005»
13 years 4 months ago
Incremental Learning of Procedural Planning Knowledge in Challenging Environments
Autonomous agents that learn about their environment can be divided into two broad classes. One class of existing learners, reinforcement learners, typically employ weak learning ...
Douglas J. Pearson, John E. Laird
IROS
2009
IEEE
168views Robotics» more  IROS 2009»
13 years 11 months ago
A stream-based hierarchical anchoring framework
— Autonomous systems situated in the real world often need to recognize, track, and reason about various types of physical objects. In order to allow reasoning at a symbolic leve...
Fredrik Heintz, Jonas Kvarnström, Patrick Doh...