HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Aharonov-Barki, R. Articles by Ruppin, E. Search for Related Content PubMed PubMed Citation Articles by Aharonov-Barki, R. Articles by Ruppin, E.

Emergence of Memory-Driven Command Neurons in Evolved Artificial Agents

Center for Computational Neuroscience, The Hebrew University, Jerusalem, Israel

Tuvik Beker

Center for Computational Neuroscience, The Hebrew University, Jerusalem, Israel

Eytan Ruppin

Department of Computer Science and Department of Physiology, School of Mathematical Sciences and School of Medicine, Tel-Aviv University, Tel-Aviv 69978, Israel

Using evolutionary simulations, we develop autonomous agents controlled by artificial neural networks (ANNs). In simple lifelike tasks of foraging and navigation, high performance levels are attained by agents equipped with fully recurrent ANN controllers. In a set of experiments sharing the same behavioral task but differing in the sensory input available to the agents, we find a common structure of a command neuron switching the dynamics of the network between radically different behavioral modes. When sensory position information is available, the command neuron reflects a map of the environment, acting as a location-dependent cell sensitive to the location and orientation of the agent. When such information is unavailable, the command neuron's activity is based on a spontaneously evolving short-term memory mechanism, which underlies its apparent place-sensitive activity. A two-parameter stochastic model for this memory mechanism is proposed. We show that the parameter values emerging from the evolutionary simulations are near optimal; evolution takes advantage of seemingly harmful features of the environment to maximize the agent's foraging efficiency. The accessibility of evolved ANNs for a detailed inspection, together with the resemblance of some of the results to known findings from neurobiology, places evolved ANNs as an excellent candidate model for the study of structure and function relationship in complex nervous systems.

This article has been cited by other articles:

				R. W. Paine and J. Tani How Hierarchical Control Self-organizes in Artificial Adaptive Systems Adaptive Behavior, September 1, 2005; 13(3): 211 - 225. [Abstract] [PDF]

				R. Aharonov, L. Segev, I. Meilijson, and E. Ruppin Localization of Function via Lesion Analysis Neural Comput., April 1, 2003; 15(4): 885 - 913. [Abstract] [Full Text] [PDF]