- Poster presentation
- Open Access
Local structure supports learning of deterministic behavior in recurrent neural networks
© Binas et al. 2015
- Published: 18 December 2015
- Reinforcement Learning
- Recurrent Neural Network
- Structural Constraint
- Learning Mechanism
- Finite Automaton
Many aspects of behavior, such as language, navigation, or logical reasoning require strongly deterministic and sequential processing of sensory and internal signals. This type of computation can be modeled conveniently in the framework of finite automata.
In this study, we present a recurrent neural network based on biologically plausible circuit motifs, which is able to learn such deterministic behavior from sensory input and reinforcement signals. We find that simple, biologically plausible structural constraints lead to optimized solutions and significantly improve the training process.
As a key result of our study, we find that simple constraints on the network topology, favoring local connectivity patterns, lead to dramatic improvements both in training time and in the optimality of the found solution, where the optimum is defined as the automaton with the minimum number of states used to implement a given behavior. These structural constraints correspond well to biological neural systems, where short-range connections far outnumber long-range ones.
- Rutishauser U, Douglas RJ: State-dependent computation using coupled recurrent networks. Neural Comput. 2009, 21 (2): 478-509.PubMedView ArticleGoogle Scholar
- Neftci E, Binas J, Rutishauser U, Chicca E, Indiveri G, Douglas JR: Synthesizing cognition in neuromorphic electronic systems. Proc Natl Acad Sci U S A. 2013, 110 (37): 3468-3476.View ArticleGoogle Scholar
- Douglas RJ, Martin KAC: Neuronal circuits of the neocortex. Annu Rev Neurosci. 2004, 27 (1): 419-451.PubMedView ArticleGoogle Scholar
- Douglas RJ, Martin KAC: Recurrent neuronal circuits in the neocortex. Curr Biol. 2007, 17 (13): 496-500.View ArticleGoogle Scholar
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.