Book contents
- Frontmatter
- Contents
- Contributors
- Introduction: Modelling perception with artificial neural networks
- Part I General themes
- Part II The use of artificial neural networks to elucidate the nature of perceptual processes in animals
- Part III Artificial neural networks as models of perceptual processing in ecology and evolutionary biology
- Part IV Methodological issues in the use of simple feedforward networks
- 14 How training and testing histories affect generalisation: a test of simple neural networks
- 15 The need for stochastic replication of ecological neural networks
- 16 Methodological issues in modelling ecological learning with neural networks
- 17 Neural network evolution and artificial life research
- 18 Current velocity shapes the functional connectivity of benthiscapes to stream insect movement
- 19 A model biological neural network: the cephalopod vestibular system
- Index
- References
17 - Neural network evolution and artificial life research
from Part IV - Methodological issues in the use of simple feedforward networks
Published online by Cambridge University Press: 05 July 2011
- Frontmatter
- Contents
- Contributors
- Introduction: Modelling perception with artificial neural networks
- Part I General themes
- Part II The use of artificial neural networks to elucidate the nature of perceptual processes in animals
- Part III Artificial neural networks as models of perceptual processing in ecology and evolutionary biology
- Part IV Methodological issues in the use of simple feedforward networks
- 14 How training and testing histories affect generalisation: a test of simple neural networks
- 15 The need for stochastic replication of ecological neural networks
- 16 Methodological issues in modelling ecological learning with neural networks
- 17 Neural network evolution and artificial life research
- 18 Current velocity shapes the functional connectivity of benthiscapes to stream insect movement
- 19 A model biological neural network: the cephalopod vestibular system
- Index
- References
Summary
17.1 Introduction
Neural networks have been employed as research tools both for machine learning applications and the simulation of artificial organisms. In recent times, much research has been undertaken on the evolution of neural networks where the architecture, weights or both are allowed to be determined by an evolutionary process such as a genetic algorithm. Much of this research is carried out with the machine learning and evolutionary computation community in mind rather than the artificial life community and as such, the latter has been slow to adopt innovative techniques which could lead to the development of complex, adaptive neural networks and in addition, shorten experiment development and design times for researchers.
This chapter attempts to address this issue by reminding researchers of the wealth of techniques that have been made available for evolutionary neural network research. Many of these techniques have been refined into freely available and well-maintained code libraries which can easily be incorporated into artificial life projects hoping to evolve neural network controllers.
The first section of this chapter outlines a review of the techniques employed to evolve neural network architectures, weights or both architectures and weights simultaneously. The encoding schemes presented in this chapter describe the encoding of multi-layer feedforward and recurrent neural networks but there are some encoding schemes which can (and have been) employed to generate more complex neural networks such as spiking (Floreano & Mattiussi, 2001; Di Paulo, 2002) and gasNets (Smith et al., 2002) which are beyond the scope of this chapter.
- Type
- Chapter
- Information
- Modelling Perception with Artificial Neural Networks , pp. 334 - 350Publisher: Cambridge University PressPrint publication year: 2010