Document Detail

Evolution of Cartesian Genetic Programs for Development of Learning Neural Architecture.
MedLine Citation:
PMID:  21591889     Owner:  NLM     Status:  Publisher    
Abstract Although artificial neural networks have taken their inspiration from natural neurological systems they have largely ignored the genetic basis of neural functions. Indeed, evolutionary approaches have mainly assumed that neural learning is associated with the adjustment of synaptic weights. The goal of this paper is to use evolutionary approaches to find suitable computational functions that are analogous to natural subcomponents of biological neurons and demonstrate that intelligent behaviour can be produced as a result of this additional biological plausibility. Our model allows neurons, dendrites, and axon branches to grow or die so that synaptic morphology can change and affect information processing while solving a computational problem. The compartmental model of neuron consists of a collection of seven chromosomes encoding distinct computational functions inside neuron. Since the equivalent computational functions of neural components are very complex and in some cases unknown, we have used a form of genetic programming known as Cartesian Genetic Programming (CGP) to obtain these functions. We start with a small random network of soma, dendrites, and neurites that develops during problem solving by executing repeatedly the seven chromosomal programs that have been found by evolution. We have evaluated the learning potential of this system in the context of a well known single agent learning problem, known as Wumpus World. We also examined the harder problem of learning in a competitive environment for two antagonistic agents, in which both agents are controlled by independent CGP Computational Networks (CGPCN). Our results show that the agents exhibit interesting learning capabilities.
Gul Muhammad Khan; Julian F Miller; David M Halliday
Related Documents :
11092149 - Individual interventions to prevent drunk driving: types, efficacy, and a theoretical p...
13677429 - Cardiovascular disease prevention in low resource settings: lessons from the heartfile ...
20422289 - Testing the universality of the effects of the communities that care prevention system ...
24567659 - The effects of student and text characteristics on the oral reading fluency of middle-g...
7772469 - Improving residents' knowledge of cancer prevention: are physicians prepared for preven...
24212169 - Oral health activities of early head start and migrant and seasonal head start programs.
24782799 - Intelligent virtual agents as language trainers facilitate multilingualism.
23759359 - Cost-effectiveness of adherence interventions for highly active antiretroviral therapy:...
18978119 - A model for instituting a comprehensive program of remediation for at-risk residents.
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2011-5-18
Journal Detail:
Title:  Evolutionary computation     Volume:  -     ISSN:  1530-9304     ISO Abbreviation:  -     Publication Date:  2011 May 
Date Detail:
Created Date:  2011-5-19     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9513581     Medline TA:  Evol Comput     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Electrical Engineering Department, NWFP UET Peshawar Pakistan.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Multimodal Optimization Using a Bi-Objective Evolutionary Algorithm.
Next Document:  Extremely low-frequency electromagnetic fields affect lipid-linked Carbonic anhydrase.