Inelligible neural networks with BP-SOM

A.J.M.M. Weijters; A.P.J. Bosch, van den; H.J. Herik, van den

doi:10.1007/BFb0026711

Inelligible neural networks with BP-SOM

A.J.M.M. Weijters, A.P.J. Bosch, van den, H.J. Herik, van den

Information Systems IE&IS

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

Abstract

Interpretation of models induced by artificial neural networks is often a difficult task. In this paper we focus on a relatively novel neural network architecture and learning algorithm, bp-som that offers possibilities to overcome this difficulty. It is shown that networks trained with BP-SOM show interesting regularities, in that hidden-unit activations become restricted to discrete values, and that the som part can be exploited for automatic rule extraction.

Original language	English
Title of host publication	Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings
Editors	C. Nédellec, C. Rouveirol
Place of Publication	Berlin
Publisher	Springer
Pages	406-411
ISBN (Print)	978-3-540-64417-0
DOIs	https://doi.org/10.1007/BFb0026711
Publication status	Published - 1998

Publication series

Name	Lecture notes in artificial intelligence
Volume	1398

Access to Document

10.1007/BFb0026711

Cite this

Weijters, A. J. M. M., Bosch, van den, A. P. J., & Herik, van den, H. J. (1998). Inelligible neural networks with BP-SOM. In C. Nédellec, & C. Rouveirol (Eds.), Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings (pp. 406-411). (Lecture notes in artificial intelligence; Vol. 1398). Springer. https://doi.org/10.1007/BFb0026711

@inproceedings{c86d289a1eb8418b89f67053fb9608ff,

title = "Inelligible neural networks with BP-SOM",

abstract = "Interpretation of models induced by artificial neural networks is often a difficult task. In this paper we focus on a relatively novel neural network architecture and learning algorithm, bp-som that offers possibilities to overcome this difficulty. It is shown that networks trained with BP-SOM show interesting regularities, in that hidden-unit activations become restricted to discrete values, and that the som part can be exploited for automatic rule extraction.",

author = "A.J.M.M. Weijters and {Bosch, van den}, A.P.J. and {Herik, van den}, H.J.",

year = "1998",

doi = "10.1007/BFb0026711",

language = "English",

isbn = "978-3-540-64417-0",

series = "Lecture notes in artificial intelligence",

publisher = "Springer",

pages = "406--411",

editor = "C. N{\'e}dellec and C. Rouveirol",

booktitle = "Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings",

}

Weijters, AJMM, Bosch, van den, APJ & Herik, van den, HJ 1998, Inelligible neural networks with BP-SOM. in C Nédellec & C Rouveirol (eds), Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings. Lecture notes in artificial intelligence, vol. 1398, Springer, Berlin, pp. 406-411. https://doi.org/10.1007/BFb0026711

Inelligible neural networks with BP-SOM. / Weijters, A.J.M.M.; Bosch, van den, A.P.J.; Herik, van den, H.J.
Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings. ed. / C. Nédellec; C. Rouveirol. Berlin: Springer, 1998. p. 406-411 (Lecture notes in artificial intelligence; Vol. 1398).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Inelligible neural networks with BP-SOM

AU - Weijters, A.J.M.M.

AU - Bosch, van den, A.P.J.

AU - Herik, van den, H.J.

PY - 1998

Y1 - 1998

N2 - Interpretation of models induced by artificial neural networks is often a difficult task. In this paper we focus on a relatively novel neural network architecture and learning algorithm, bp-som that offers possibilities to overcome this difficulty. It is shown that networks trained with BP-SOM show interesting regularities, in that hidden-unit activations become restricted to discrete values, and that the som part can be exploited for automatic rule extraction.

AB - Interpretation of models induced by artificial neural networks is often a difficult task. In this paper we focus on a relatively novel neural network architecture and learning algorithm, bp-som that offers possibilities to overcome this difficulty. It is shown that networks trained with BP-SOM show interesting regularities, in that hidden-unit activations become restricted to discrete values, and that the som part can be exploited for automatic rule extraction.

U2 - 10.1007/BFb0026711

DO - 10.1007/BFb0026711

M3 - Conference contribution

SN - 978-3-540-64417-0

T3 - Lecture notes in artificial intelligence

SP - 406

EP - 411

BT - Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings

A2 - Nédellec, C.

A2 - Rouveirol, C.

PB - Springer

CY - Berlin

ER -

Inelligible neural networks with BP-SOM

Abstract

Publication series

Access to Document

Fingerprint

Cite this