Credit assignment among neurons in co-evolving populations

Vineet R. KHARE; Xin YAO; Bernhard SENDHOFF

doi:10.1007/978-3-540-30217-9_89

Credit assignment among neurons in co-evolving populations

Vineet R. KHARE
, Xin YAO
, Bernhard SENDHOFF

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

18 Citations (Scopus)

Abstract

Different credit assignment strategies are investigated in a two level co-evolutionary model which involves a population of Gaussian neurons and a population of radial basis function networks consisting of neurons from the neuron population. Each individual in neuron population can contribute to one or more networks in network population, so there is a two-fold difficulty in evaluating the effectiveness (or fitness) of a neuron. Firstly, since each neuron only represents a partial solution to the problem, it needs to be assigned some credit for the complete problem solving activity. Secondly, these credits need to be accumulated from different networks the neuron participates in. This model, along with various credit assignment strategies, is tested on a classification (Heart disease diagnosis problem from UCI machine learning repository) and a regression problem (Mackey-Glass time series prediction problem). © Springer-Verlag 2004.

Original language	English
Title of host publication	Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings
Editors	Xin YAO, Edmund K. BURKE, José A. LOZANO, Jim SMITH, Juan Julián MERELO-GUERVÓS, John A. BULLINARIA, Jonathan E. ROWE, Peter TIŇO, Ata KABÁN, Hans-Paul SCHWEFEL
Publisher	Springer Berlin Heidelberg
Pages	882-891
Number of pages	10
ISBN (Electronic)	9783540302179
ISBN (Print)	9783540230922
DOIs	https://doi.org/10.1007/978-3-540-30217-9_89
Publication status	Published - 2004
Externally published	Yes
Event	8th International Conference on Parallel Problem Solving from Nature, PPSN 2004 - Birmingham, United Kingdom Duration: 18 Sept 2004 → 22 Sept 2004

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin, Heidelberg
Volume	3242
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	8th International Conference on Parallel Problem Solving from Nature, PPSN 2004
Country/Territory	United Kingdom
City	Birmingham
Period	18/09/04 → 22/09/04

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 8 Decent Work and Economic Growth

Keywords

Neuron Population
Radial Basis Function Network
Assignment Strategy
Cooperative Coevolution
Credit Assignment

Access to Document

10.1007/978-3-540-30217-9_89

Cite this

KHARE, V. R., YAO, X., & SENDHOFF, B. (2004). Credit assignment among neurons in co-evolving populations. In X. YAO, E. K. BURKE, J. A. LOZANO, J. SMITH, J. J. MERELO-GUERVÓS, J. A. BULLINARIA, J. E. ROWE, P. TIŇO, A. KABÁN, & H.-P. SCHWEFEL (Eds.), Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings (pp. 882-891). (Lecture Notes in Computer Science; Vol. 3242). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-30217-9_89

KHARE, Vineet R. ; YAO, Xin ; SENDHOFF, Bernhard. / Credit assignment among neurons in co-evolving populations. Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings. editor / Xin YAO ; Edmund K. BURKE ; José A. LOZANO ; Jim SMITH ; Juan Julián MERELO-GUERVÓS ; John A. BULLINARIA ; Jonathan E. ROWE ; Peter TIŇO ; Ata KABÁN ; Hans-Paul SCHWEFEL. Springer Berlin Heidelberg, 2004. pp. 882-891 (Lecture Notes in Computer Science).

@inproceedings{f26a1b62a05f48dba55d0ce835f14758,

title = "Credit assignment among neurons in co-evolving populations",

abstract = "Different credit assignment strategies are investigated in a two level co-evolutionary model which involves a population of Gaussian neurons and a population of radial basis function networks consisting of neurons from the neuron population. Each individual in neuron population can contribute to one or more networks in network population, so there is a two-fold difficulty in evaluating the effectiveness (or fitness) of a neuron. Firstly, since each neuron only represents a partial solution to the problem, it needs to be assigned some credit for the complete problem solving activity. Secondly, these credits need to be accumulated from different networks the neuron participates in. This model, along with various credit assignment strategies, is tested on a classification (Heart disease diagnosis problem from UCI machine learning repository) and a regression problem (Mackey-Glass time series prediction problem). {\textcopyright} Springer-Verlag 2004.",

keywords = "Neuron Population, Radial Basis Function Network, Assignment Strategy, Cooperative Coevolution, Credit Assignment",

author = "KHARE, \{Vineet R.\} and Xin YAO and Bernhard SENDHOFF",

year = "2004",

doi = "10.1007/978-3-540-30217-9\_89",

language = "English",

isbn = "9783540230922",

series = "Lecture Notes in Computer Science",

publisher = "Springer Berlin Heidelberg",

pages = "882--891",

editor = "Xin YAO and BURKE, \{Edmund K.\} and LOZANO, \{Jos{\'e} A.\} and Jim SMITH and MERELO-GUERV{\'O}S, \{Juan Juli{\'a}n\} and BULLINARIA, \{John A.\} and ROWE, \{Jonathan E.\} and Peter TI{\v N}O and Ata KAB{\'A}N and Hans-Paul SCHWEFEL",

booktitle = "Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings",

note = "8th International Conference on Parallel Problem Solving from Nature, PPSN 2004 ; Conference date: 18-09-2004 Through 22-09-2004",

}

KHARE, VR, YAO, X & SENDHOFF, B 2004, Credit assignment among neurons in co-evolving populations. in X YAO, EK BURKE, JA LOZANO, J SMITH, JJ MERELO-GUERVÓS, JA BULLINARIA, JE ROWE, P TIŇO, A KABÁN & H-P SCHWEFEL (eds), Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings. Lecture Notes in Computer Science, vol. 3242, Springer Berlin Heidelberg, pp. 882-891, 8th International Conference on Parallel Problem Solving from Nature, PPSN 2004, Birmingham, United Kingdom, 18/09/04. https://doi.org/10.1007/978-3-540-30217-9_89

Credit assignment among neurons in co-evolving populations. / KHARE, Vineet R.; YAO, Xin; SENDHOFF, Bernhard.
Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings. ed. / Xin YAO; Edmund K. BURKE; José A. LOZANO; Jim SMITH; Juan Julián MERELO-GUERVÓS; John A. BULLINARIA; Jonathan E. ROWE; Peter TIŇO; Ata KABÁN; Hans-Paul SCHWEFEL. Springer Berlin Heidelberg, 2004. p. 882-891 (Lecture Notes in Computer Science; Vol. 3242).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Credit assignment among neurons in co-evolving populations

AU - KHARE, Vineet R.

AU - YAO, Xin

AU - SENDHOFF, Bernhard

PY - 2004

Y1 - 2004

N2 - Different credit assignment strategies are investigated in a two level co-evolutionary model which involves a population of Gaussian neurons and a population of radial basis function networks consisting of neurons from the neuron population. Each individual in neuron population can contribute to one or more networks in network population, so there is a two-fold difficulty in evaluating the effectiveness (or fitness) of a neuron. Firstly, since each neuron only represents a partial solution to the problem, it needs to be assigned some credit for the complete problem solving activity. Secondly, these credits need to be accumulated from different networks the neuron participates in. This model, along with various credit assignment strategies, is tested on a classification (Heart disease diagnosis problem from UCI machine learning repository) and a regression problem (Mackey-Glass time series prediction problem). © Springer-Verlag 2004.

AB - Different credit assignment strategies are investigated in a two level co-evolutionary model which involves a population of Gaussian neurons and a population of radial basis function networks consisting of neurons from the neuron population. Each individual in neuron population can contribute to one or more networks in network population, so there is a two-fold difficulty in evaluating the effectiveness (or fitness) of a neuron. Firstly, since each neuron only represents a partial solution to the problem, it needs to be assigned some credit for the complete problem solving activity. Secondly, these credits need to be accumulated from different networks the neuron participates in. This model, along with various credit assignment strategies, is tested on a classification (Heart disease diagnosis problem from UCI machine learning repository) and a regression problem (Mackey-Glass time series prediction problem). © Springer-Verlag 2004.

KW - Neuron Population

KW - Radial Basis Function Network

KW - Assignment Strategy

KW - Cooperative Coevolution

KW - Credit Assignment

UR - https://www.scopus.com/pages/publications/35048891596

U2 - 10.1007/978-3-540-30217-9_89

DO - 10.1007/978-3-540-30217-9_89

M3 - Conference paper (refereed)

SN - 9783540230922

T3 - Lecture Notes in Computer Science

SP - 882

EP - 891

BT - Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings

A2 - YAO, Xin

A2 - BURKE, Edmund K.

A2 - LOZANO, José A.

A2 - SMITH, Jim

A2 - MERELO-GUERVÓS, Juan Julián

A2 - BULLINARIA, John A.

A2 - ROWE, Jonathan E.

A2 - TIŇO, Peter

A2 - KABÁN, Ata

A2 - SCHWEFEL, Hans-Paul

PB - Springer Berlin Heidelberg

T2 - 8th International Conference on Parallel Problem Solving from Nature, PPSN 2004

Y2 - 18 September 2004 through 22 September 2004

ER -

KHARE VR, YAO X, SENDHOFF B. Credit assignment among neurons in co-evolving populations. In YAO X, BURKE EK, LOZANO JA, SMITH J, MERELO-GUERVÓS JJ, BULLINARIA JA, ROWE JE, TIŇO P, KABÁN A, SCHWEFEL HP, editors, Parallel Problem Solving from Nature : PPSN VIII : 8th International Conference, Birmingham, UK, September 18-22, 2004, Proceedings. Springer Berlin Heidelberg. 2004. p. 882-891. (Lecture Notes in Computer Science). doi: 10.1007/978-3-540-30217-9_89

Credit assignment among neurons in co-evolving populations

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this