Artificial biochemical networks: a different connectionist paradigm.

MacLeod, Christopher; Capanni, Niccolo F.

Abstract

Connectionist models are usually based on artificial neural networks. However, there is another route towards parallel distributed processing. This is by considering the origins of the intelligence displayed by the single celled organisms known as protoctists. Such intelligence arises by means of the biochemical interactions within the animal. An artificial model of this might therefore be termed an artificial biochemical network or ABN. This paper describes the attributes of such networks and illustrates their abilities in pattern recognition problems and in generating time-varying signals of a type which can be used in many control tasks. The flexibility of the system is explained using legged robots as an example. The networks are trained using back propagation and evolutionary algorithms such as genetic algorithms.

Citation

MACLEOD, C. and CAPANNI, N.F. 2010. Artificial biochemical networks: a different connectionist paradigm. Artificial intelligence review [online], 33(1-2), pages 123-134. Available from: https://doi.org/10.1007/s10462-009-9149-y

• Journal Article Type: Article
• Acceptance Date: Nov 18, 2009
• Online Publication Date: Nov 18, 2009
• Publication Date: Feb 28, 2010
• Deposit Date: Jan 29, 2010
• Publicly Available Date: Jan 29, 2010
• Journal: Artificial intelligence review
• Print ISSN: 0269-2821
• Electronic ISSN: 1573-7462
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 33
• Issue: 1-2
• Pages: 123-134
• DOI: https://doi.org/10.1007/s10462-009-9149-y
• Keywords: Artificial neural network; Protozoa; Evolutionary algorithm; Connectionism; Biochemistry; Protein; Robot; Pattern recognition
• Public URL: http://hdl.handle.net/10059/455
• Contract Date: Jan 29, 2010