Which model to use for the Liquid State Machine?

Author

Grzyb, Beata J. ; Chinellato, Eris ; Wojcik, Grzegorz M. ; Kaminski, Wieslaw A.

Author_Institution

Comput. Sci. & Eng. Dept., Jaume I Univ., Castellon, Spain

fYear

2009

fDate

14-19 June 2009

Firstpage

1018

Lastpage

1024

Abstract

The properties of separation ability and computational efficiency of liquid state machines depend on the neural model employed and on the connection density in the liquid column. A simple model of part of mammalians visual system consisting of one hypercolumn was examined. Such a system was stimulated by two different input patterns, and the Euclidean distance, as well as the partial and global entropy of the liquid column responses were calculated. Interesting insights could be drawn regarding the properties of different neural models used in the liquid hypercolumn, and on the effect of connection density on the information representation capability of the system.

Keywords

brain; neurophysiology; Euclidean distance; brain cortex; liquid column responses; liquid hypercolumn; liquid state machine; mammalians visual system; neural model; Biological neural networks; Biological system modeling; Biology computing; Computational efficiency; Computer science; Euclidean distance; Intelligent robots; Neurons; Performance analysis; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2009. IJCNN 2009. International Joint Conference on

Conference_Location

Atlanta, GA

ISSN

1098-7576

Print_ISBN

978-1-4244-3548-7

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2009.5178822

Filename

5178822