This study describes how complex goal-directed behavior can evolve in a hierarchically organized recurrent neural network controlling a simulated Khepera robot. Different types of ...
Given an adequate simulation model of the task environment and payoff function that measures the quality of partially successful plans, competition-based heuristics such as geneti...
The aim of this tool paper is twofold: First we show that VipTool [9, 2] can now synthesize Petri nets from partially ordered runs. To integrate this extension and further new func...
Traditional knowledge representations were developed to encode complete, explicit and executable programs, a goal that makes them less than ideal for representing the incomplete an...
We describe a new system for building Tablet PC-based classroom software. The system, called SLICE, is built for extensibility, using a unique "explicit state" model. Ap...
Sam Kamin, Michael Hines, Chad Peiper, Boris Capit...