Towards Computational Neural Systems through Developmental Evolution

A.G. Rust; R.G. Adams; S. George; H. Bolouri

doi:10.1007/3-540-44597-8

Towards Computational Neural Systems through Developmental Evolution

A.G. Rust, R.G. Adams, S. George, H. Bolouri

Centre for Computer Science and Informatics Research

Research output: Contribution to journal › Article › peer-review

Abstract

The capability of creating artificial neural networks with biologically-plausible characteristics, is becoming ever more attainable through the greater understanding of biological neural systems and the constant increases in available desktop computing power. Designing and implementing such neural systems still however remains a complex and challenging problem. This chapter introduces a design methodology, inspired by embryonic neural development, which is capable of creating 3 dimensional morphologies of both individual neurons and networks. Examples of such morphologies are given, which are created by evolving the parameters of the developmental model using an evolutionary algorithm.

Original language	English
Pages (from-to)	188-202
Journal	Lecture Notes in Computer Science (LNCS)
Volume	2036
DOIs	https://doi.org/10.1007/3-540-44597-8
Publication status	Published - 2001

Access to Document

10.1007/3-540-44597-8

Cite this

@article{2b572182158c41b488155f538b28d470,

title = "Towards Computational Neural Systems through Developmental Evolution",

abstract = "The capability of creating artificial neural networks with biologically-plausible characteristics, is becoming ever more attainable through the greater understanding of biological neural systems and the constant increases in available desktop computing power. Designing and implementing such neural systems still however remains a complex and challenging problem. This chapter introduces a design methodology, inspired by embryonic neural development, which is capable of creating 3 dimensional morphologies of both individual neurons and networks. Examples of such morphologies are given, which are created by evolving the parameters of the developmental model using an evolutionary algorithm.",

author = "A.G. Rust and R.G. Adams and S. George and H. Bolouri",

note = "“The original publication is available at www.springerlink.com”. Copyright Springer. DOI: 10.1007/3-540-44597-8_14 [Full text of this article is not available in the UHRA]",

year = "2001",

doi = "10.1007/3-540-44597-8",

language = "English",

volume = "2036",

pages = "188--202",

journal = "Lecture Notes in Computer Science (LNCS)",

issn = "0302-9743",

publisher = "Springer Nature Link",

}

TY - JOUR

T1 - Towards Computational Neural Systems through Developmental Evolution

AU - Rust, A.G.

AU - Adams, R.G.

AU - George, S.

AU - Bolouri, H.

N1 - “The original publication is available at www.springerlink.com”. Copyright Springer. DOI: 10.1007/3-540-44597-8_14 [Full text of this article is not available in the UHRA]

PY - 2001

Y1 - 2001

N2 - The capability of creating artificial neural networks with biologically-plausible characteristics, is becoming ever more attainable through the greater understanding of biological neural systems and the constant increases in available desktop computing power. Designing and implementing such neural systems still however remains a complex and challenging problem. This chapter introduces a design methodology, inspired by embryonic neural development, which is capable of creating 3 dimensional morphologies of both individual neurons and networks. Examples of such morphologies are given, which are created by evolving the parameters of the developmental model using an evolutionary algorithm.

AB - The capability of creating artificial neural networks with biologically-plausible characteristics, is becoming ever more attainable through the greater understanding of biological neural systems and the constant increases in available desktop computing power. Designing and implementing such neural systems still however remains a complex and challenging problem. This chapter introduces a design methodology, inspired by embryonic neural development, which is capable of creating 3 dimensional morphologies of both individual neurons and networks. Examples of such morphologies are given, which are created by evolving the parameters of the developmental model using an evolutionary algorithm.

U2 - 10.1007/3-540-44597-8

DO - 10.1007/3-540-44597-8

M3 - Article

SN - 0302-9743

VL - 2036

SP - 188

EP - 202

JO - Lecture Notes in Computer Science (LNCS)

JF - Lecture Notes in Computer Science (LNCS)

ER -

Towards Computational Neural Systems through Developmental Evolution

Abstract

Access to Document

Fingerprint

Cite this