Evolution of Cartesian Genetic Programs for Development of Learning Neural Architecture
- 1 September 2011
- journal article
- research article
- Published by MIT Press in Evolutionary Computation
- Vol. 19 (3) , 469-523
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 sub-components of biological neurons and demonstrate that intelligent behavior 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 a neuron consists of a collection of seven chromosomes encoding distinct computational functions inside the 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 repeatedly executing 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.Keywords
This publication has 37 references indexed in Scilit:
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- DENDRITIC COMPUTATIONAnnual Review of Neuroscience, 2005
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Synaptic tagging and long-term potentiationNature, 1997
- Mechanism of synapse disassembly at the developing neuromuscular junctionCurrent Opinion in Neurobiology, 1996
- Coevolutionary ComputationArtificial Life, 1995
- Cell division and migration in a ‘genotype’ for neural networksNetwork: Computation in Neural Systems, 1994
- Synaptic plasticity in the hippocampus: LTP and LTDCell, 1994
- Activity-dependent Outgrowth of Neurons and Overshoot Phenomena in Developing Neural NetworksJournal of Theoretical Biology, 1994
- Mathematical models for cellular interactions in development I. Filaments with one-sided inputsJournal of Theoretical Biology, 1968