Process Identification through modular neural networks and rule extraction

B J vanderZwaag; C H Slump; Lambert Spaanenburg

Process Identification through modular neural networks and rule extraction

B J vanderZwaag, C H Slump, Lambert Spaanenburg

External Organization - Unknown

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

Monolithic neural networks may be trained from measured data to establish knowledge about the process. Unfortunately, this knowledge is not guaranteed to be found and – if at all – hard to extract. Modular neural networks are better suited for this purpose. Domain-ordered by topology, rule extraction is performed module by module. This has all the benefits of a divide-and-conquer method and opens the way to structured design. This paper discusses a next step in this direction by illustrating the potential of base functions to design the neural model

Original language	English
Title of host publication	Proceedings FLINS 2002
Pages	268-277
Publication status	Published - 2002
Externally published	Yes
Event	5th International Conference on Computational Intelligent Systems for Applied Research (FLINS) - Gent, Belgium Duration: 2002 Sept 16 → 2002 Sept 18

Conference

Conference	5th International Conference on Computational Intelligent Systems for Applied Research (FLINS)
Country/Territory	Belgium
City	Gent
Period	2002/09/16 → 2002/09/18

Subject classification (UKÄ)

Electrical Engineering, Electronic Engineering, Information Engineering

Free keywords

Neural Networks
Modularity
Functional Base
Process Model
Rule Extraction

Cite this

@inproceedings{a7fb62aca8cf4f96a6c8ccfc0c1da9fc,

title = "Process Identification through modular neural networks and rule extraction",

abstract = "Monolithic neural networks may be trained from measured data to establish knowledge about the process. Unfortunately, this knowledge is not guaranteed to be found and – if at all – hard to extract. Modular neural networks are better suited for this purpose. Domain-ordered by topology, rule extraction is performed module by module. This has all the benefits of a divide-and-conquer method and opens the way to structured design. This paper discusses a next step in this direction by illustrating the potential of base functions to design the neural model",

keywords = "Neural Networks, Modularity, Functional Base, Process Model, Rule Extraction",

author = "vanderZwaag, {B J} and Slump, {C H} and Lambert Spaanenburg",

year = "2002",

language = "English",

pages = "268--277",

booktitle = "Proceedings FLINS 2002",

note = "5th International Conference on Computational Intelligent Systems for Applied Research (FLINS) ; Conference date: 16-09-2002 Through 18-09-2002",

}

TY - GEN

T1 - Process Identification through modular neural networks and rule extraction

AU - vanderZwaag, B J

AU - Slump, C H

AU - Spaanenburg, Lambert

PY - 2002

Y1 - 2002

N2 - Monolithic neural networks may be trained from measured data to establish knowledge about the process. Unfortunately, this knowledge is not guaranteed to be found and – if at all – hard to extract. Modular neural networks are better suited for this purpose. Domain-ordered by topology, rule extraction is performed module by module. This has all the benefits of a divide-and-conquer method and opens the way to structured design. This paper discusses a next step in this direction by illustrating the potential of base functions to design the neural model

AB - Monolithic neural networks may be trained from measured data to establish knowledge about the process. Unfortunately, this knowledge is not guaranteed to be found and – if at all – hard to extract. Modular neural networks are better suited for this purpose. Domain-ordered by topology, rule extraction is performed module by module. This has all the benefits of a divide-and-conquer method and opens the way to structured design. This paper discusses a next step in this direction by illustrating the potential of base functions to design the neural model

KW - Neural Networks

KW - Modularity

KW - Functional Base

KW - Process Model

KW - Rule Extraction

M3 - Paper in conference proceeding

SP - 268

EP - 277

BT - Proceedings FLINS 2002

T2 - 5th International Conference on Computational Intelligent Systems for Applied Research (FLINS)

Y2 - 16 September 2002 through 18 September 2002

ER -

Process Identification through modular neural networks and rule extraction

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Fingerprint

Cite this