Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Computational Consequences of a Bias toward Short Connections

Computational Consequences of a Bias toward Short Connections A fundamental observation in the neurosciences is that the brain is a modular system in which different regions perform different tasks. Recent evidence, however, raises questions about the accuracy of this characterization with respect to neo-nates. One possible interpretation of this evidence is that certain aspects of the modular organization of the adult brain arise developmentally. To explore this hypothesis we wish to characterize the computational principles that underlie the development of modular systems. In previous work we have considered computational schemes that allow a learning system to discover the modular structure that is present in the environment (Jacobs, Jordan, & Barto, 1991). In the current paper we present a complementary approach in which the development of modularity is due to an architectural bias in the learner. In particular, we examine the computational consequences of a simple architectural bias toward short-range connections. We present simulations that show that systems that learn under the influence of such a bias have a number of desirable properties, including a tendency to decompose tasks into subtasks, to decouple the dynamics of recurrent subsystems, and to develop location-sensitive internal representations. Furthermore, the system's units develop local receptive and projective fields, and the system develops characteristics that are typically associated with topographic maps. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Cognitive Neuroscience MIT Press

Computational Consequences of a Bias toward Short Connections

Loading next page...
 
/lp/mit-press/computational-consequences-of-a-bias-toward-short-connections-rG25AEYoLX

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
MIT Press
Copyright
© 1992 by the Massachusetts Institute of Technology
ISSN
0898-929X
eISSN
1530-8898
DOI
10.1162/jocn.1992.4.4.323
pmid
23968126
Publisher site
See Article on Publisher Site

Abstract

A fundamental observation in the neurosciences is that the brain is a modular system in which different regions perform different tasks. Recent evidence, however, raises questions about the accuracy of this characterization with respect to neo-nates. One possible interpretation of this evidence is that certain aspects of the modular organization of the adult brain arise developmentally. To explore this hypothesis we wish to characterize the computational principles that underlie the development of modular systems. In previous work we have considered computational schemes that allow a learning system to discover the modular structure that is present in the environment (Jacobs, Jordan, & Barto, 1991). In the current paper we present a complementary approach in which the development of modularity is due to an architectural bias in the learner. In particular, we examine the computational consequences of a simple architectural bias toward short-range connections. We present simulations that show that systems that learn under the influence of such a bias have a number of desirable properties, including a tendency to decompose tasks into subtasks, to decouple the dynamics of recurrent subsystems, and to develop location-sensitive internal representations. Furthermore, the system's units develop local receptive and projective fields, and the system develops characteristics that are typically associated with topographic maps.

Journal

Journal of Cognitive NeuroscienceMIT Press

Published: Oct 1, 1992

There are no references for this article.