Implementation of finite state automata using fLIF neurons

This paper presents a novel approach to implementation of finite state automaton (FSA) using fatiguing Leaky Integrate and Fire (fLIF) neurons. This approach uses fLIF neurons because they are a model of biological neurons that closely approximates the basic functions of neurons. FSAs are an important mechanism for processing information. In this paper, the creation and implementation of two FSA models is described; the results show that all input sentences are correctly marked as acceptable or unacceptable.

[1]  Christian R. Huyck,et al.  Creating hierarchical categories using cell assemblies , 2007, Connect. Sci..

[2]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Christian Huyck,et al.  Parsing with fLIF Neurons , 2007 .

[4]  Christos H. Papadimitriou,et al.  Elements of the Theory of Computation , 1997, SIGA.

[5]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[6]  C. Huyck,et al.  CABot1: A videogame agent implemented in fLIF neurons , 2008, 2008 7th IEEE International Conference on Cybernetic Intelligent Systems.

[7]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[8]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.