NNRG Areas - Concept and Schema Learning

neural networks research group

Concept and Schema Learning

An agent can truly understand the meaning of its knowledge structures, and utilize them most effectively, only if that knowledge is grounded on sensorimotor interactions with the world. We aim at building systems that learn such grounded representations, from basic causal concepts to high-level schemas of visual scenes.

Wee Kheng Leow Risto Miikkulainen Jefferson Provost Gert Westermann Paul Williams Dagmar (Dasa) Zeithamova

1-5 6-10 11-15 16-17 View All 17

Category Learning Systems (2008) Self-Organizing Distinctive State Abstraction Using Options (2007) Grounding Language in Descriptions of Scenes (2006) Self-Organizing Perceptual and Temporal Abstraction for Robot Reinforcement Learning (2004) Constructivist Learning: A Neural Implementation of the Schema Mechanism (2003)

Learning Schemas for Robot Perception CLA: The Constructivist Learning Architecture Schema-Based Object Recognition and Scene Analysis: The VISOR System

HFM FGREPNET DISLEX