Concepts from Data

  • Brandon Rohrer
  • Published 2009 in
    AAAI Fall Symposium: Biologically Inspired…


Creating new concepts from data is a hard problem in the development of cognitive architectures, but one that must be solved for the BICA community to declare success. Two concept generation algorithms are presented here that are appropriate to different levels of concept abstraction: statespace partitioning with decision trees and context-based similarity. 


5 Figures and Tables

Slides referencing similar topics