Incremental growth in modular neural networks

Authors:
Christopher MacLeod;Grant Maxwell;Sethuraman Muthuraman
Affiliations:
School of Engineering, The Robert Gordon University, Schoolhill, Aberdeen AB10 1FR, Scotland, UK;School of Engineering, The Robert Gordon University, Schoolhill, Aberdeen AB10 1FR, Scotland, UK;School of Engineering, The Robert Gordon University, Schoolhill, Aberdeen AB10 1FR, Scotland, UK
Venue:
Engineering Applications of Artificial Intelligence
Year:
2009

Citing 10
Cited 2

The cascade-correlation learning architecture

Advances in neural information processing systems 2
Automatic definition of modular neural networks

Adaptive Behavior
Evolution of the ancestral vertebrate brain

The handbook of brain theory and neural networks
Recent developments in the evolution of morphologies and controllers for physically simulated creatures

Artificial Life
Genetic Synthesis of Modular Neural Networks

Proceedings of the 5th International Conference on Genetic Algorithms
Evolutionary Artificial Neural Networks for Quadruped Locomotion

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Modular Genetic Neural Networks for Six-Legged Locomotion

AE '95 Selected Papers from the European conference on Artificial Evolution
Creating high-level components with a generative representation for body-brain evolution

Artificial Life
Artificial BioChemical Networks

CIMCA '05 Proceedings of the International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce Vol-2 (CIMCA-IAWTIC'06) - Volume 02
The evolution of modular artificial neural networks for legged robot control

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing

Artificial biochemical networks: a different connectionist paradigm

Artificial Intelligence Review
Temporal patterns in artificial reaction networks

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper outlines an algorithm for incrementally growing Artificial Neural Networks. The algorithm allows the network to expand by adding new sub-networks or modules to an existing structure; the modules are trained using an Evolutionary Algorithm. Only the latest module added to the network is trained, the previous structure remains fixed. The algorithm allows information from different data domains to be integrated into the network and because the search space in each iteration is small, large and complex networks with a modular structure can emerge naturally. The paper describes an application of the algorithm to a legged robot and discusses its biological inspiration.