Artificial biochemical networks.

Capanni, N.; MacLeod, C.; Maxwell, G.; Clayton, W.

Abstract

Connectionist approaches to Artificial Intelligence are almost always based on Artificial Neural Networks. However, there is another route towards Parallel Distributed Processing, taking as its inspiration the intelligence displayed by single celled creatures called Protoctists (Protists). This is based on networks of interacting proteins. Such networks may be used in Pattern Recognition and Control tasks and are more flexible than most neuron models. In this paper they are demonstrated in Image Recognition applications and in Legged Robot control. They are trained using a Genetic Algorithm and Back Propagation.

Citation

CAPANNI, N., MACLEOD, C., MAXWELL, G. and CLAYTON, W. 2005. Artificial biochemical networks. In Mohammadlan, M. (ed.) Proceedings of the 2005 International conference on computational intelligence for modelling, control and automation, and the 2005 International conference on intelligent agents, web technologies and internet commerce (CIMCA-IAWTIC'05), 28-30 November 2005, Vienna, Austria. Los Alamitos: IEEE Computer Society [online], volume 2, article number 1631452, pages 98-102. Available from: https://doi.org/10.1109/CIMCA.2005.1631452

• Conference Name: 2005 International conference on computational intelligence for modelling, control and automation, and the 2005 International conference on intelligent agents, web technologies and internet commerce (CIMCA-IAWTIC'05)
• Conference Location: Vienna, Austria
• Start Date: Nov 28, 2005
• End Date: Nov 30, 2005
• Acceptance Date: Nov 28, 2005
• Online Publication Date: Dec 31, 2005
• Publication Date: Dec 31, 2005
• Deposit Date: Feb 17, 2009
• Publicly Available Date: Feb 17, 2009
• Publisher: IEEE Computer Society
• Volume: 2
• Article Number: 1631452
• Pages: 98-102
• ISBN: 0769525040
• DOI: https://doi.org/10.1109/CIMCA.2005.1631452
• Keywords: Artificial intelligence; Parallel distributed processing; Protoctists; Image recognition; Legged robot control
• Public URL: http://hdl.handle.net/10059/306