Communicating neurons: a connectionist spiking neuron implementation of stochastic diffusion search

Nasuto, S. J. ORCID: https://orcid.org/0000-0001-9414-9049, Bishop, J. M. and De Meyer, K. (2009) Communicating neurons: a connectionist spiking neuron implementation of stochastic diffusion search. Neurocomputing, 72 (4-6). pp. 704-712. ISSN 0925-2312 doi: 10.1016/j.neucom.2008.03.019

Abstract/Summary

An information processing paradigm in the brain is proposed, instantiated in an artificial neural network using biologically motivated temporal encoding. The network will locate within the external world stimulus, the target memory, defined by a specific pattern of micro-features. The proposed network is robust and efficient. Akin in operation to the swarm intelligence paradigm, stochastic diffusion search, it will find the best-fit to the memory with linear time complexity. information multiplexing enables neurons to process knowledge as 'tokens' rather than 'types'. The network illustrates possible emergence of cognitive processing from low level interactions such as memory retrieval based on partial matching. (C) 2007 Elsevier B.V. All rights reserved.

Additional Information	2nd International Conference on Brain Inspired Cognitive Systems (BICS 2006) OCT 10-14, 2006 Lesvos, GREECE
Item Type	Article
URI	https://reading-clone.eprints-hosting.org/id/eprint/15345
Item Type	Article
Refereed	Yes
Divisions	Life Sciences > School of Biological Sciences > Department of Bio-Engineering
Uncontrolled Keywords	Spiking neural networks, Selective attention, Stochastic diffusion, search, Swarm intelligence, Global search, PATTERN-RECOGNITION, COMPUTATION, CORTEX
Additional Information	2nd International Conference on Brain Inspired Cognitive Systems (BICS 2006) OCT 10-14, 2006 Lesvos, GREECE
Download/View statistics	View download statistics for this item