Neuroevolution based on reusable and hierarchical modular representation

Authors:
Takumi Kamioka;Eiji Uchibe;Kenji Doya
Affiliations:
Okinawa Institute of Science and Technology, Okinawa, Japan and Nara Institute of Science and Technology, Nara, Japan;Okinawa Institute of Science and Technology, Okinawa, Japan;Okinawa Institute of Science and Technology, Okinawa, Japan and Nara Institute of Science and Technology, Nara, Japan and ATR Computational Neuroscience Laboratories, Kyoto, Japan
Venue:
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Year:
2008

Citing 15
Cited 0

Automatic definition of modular neural networks

Adaptive Behavior
“Genotypes” for neural networks

The handbook of brain theory and neural networks
Evolving neural networks through augmenting topologies

Evolutionary Computation
Completely Derandomized Self-Adaptation in Evolution Strategies

Evolutionary Computation
Evolving neural networks

Proceedings of the 9th annual conference companion on Genetic and evolutionary computation
Acquiring evolvability through adaptive representations

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Evolutionary reinforcement learning of artificial neural networks

International Journal of Hybrid Intelligent Systems - Hybridization of Intelligent Systems
Accelerated Neural Evolution through Cooperatively Coevolved Synapses

The Journal of Machine Learning Research
A comparison between cellular encoding and direct encoding for genetic neural networks

GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
A case study on the critical role of geometric regularity in machine learning

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Darwinian embodied evolution of the learning ability for survival

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Neuroevolution with analog genetic encoding

PPSN'06 Proceedings of the 9th international conference on Parallel Problem Solving from Nature
Evolutionary Development of Hierarchical Learning Structures

IEEE Transactions on Evolutionary Computation
Analog Genetic Encoding for the Evolution of Circuits and Networks

IEEE Transactions on Evolutionary Computation
The Automatic Acquisition, Evolution and Reuse of Modules in Cartesian Genetic Programming

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The framework of neuroevolution (NE) provides a way of finding appropriate structures as well as connection weights of artificial neural networks. However, the conventional NE approach of directly coding each connection weight by a gene is severely limited in its scalability and evolvability. In this study, we propose a novel indirect coding approach in which a phenotypical network develops from the genes encoding multiple subnetwork modules. Each gene encodes a subnetwork consisting of the input, hidden, and output nodes and connections between them. A connection can be a real weight or a pointer to another subnetwork. The structure of the network evolves by inserting new connection weights or subnetworks, merging two subnetworks as a higherlevel subnetwork, or changing the existing connections. We investigated the evolutionary process of the network structure using the task of double pole balancing. We confirmed that the proposed method by the modular developmental rule can produce a wide variety of network architectures and that evolution can trim them down to the most appropriate ones required by the task.