System identification with dynamic neural networks

Prasanta K. De; Massoud Amin; Ervin Y. Rodin

System identification with dynamic neural networks

Prasanta K. De
, Massoud Amin
, Ervin Y. Rodin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The application of dynamic neurons to system identification is investigated. Similar networks can easily be extended to the control of systems in an open- or closed-loop fashion. States of the dynamic neurons evolve as x = -ax+bu, where u is the input to a neuron. The output of the dynamic neurons are given by y = λ(x), where λ(.) is a nonlinear function. The Distributed Dynamic Back Propagation (DDBP) technique is used to back propagate the hierarchical-network output errors. This implementation is useful because it yields a common platform on which many identification and control problems can be investigated.

Original language	English (US)
Title of host publication	Intelligent Engineering Systems Through Artificial Neural Networks
Editors	C.H. Dagli, L.I. Burke, Y.C. Shin
Publisher	ASME
Pages	97-102
Number of pages	6
Volume	2
State	Published - Dec 1 1992
Externally published	Yes
Event	Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA Duration: Nov 15 1992 → Nov 18 1992

Other

Other	Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92
City	St.Louis, MO, USA
Period	11/15/92 → 11/18/92

Find It

Find It at U of M Libraries

Cite this

@inproceedings{37fe91231dae4a9ab89706da44309353,

title = "System identification with dynamic neural networks",

abstract = "The application of dynamic neurons to system identification is investigated. Similar networks can easily be extended to the control of systems in an open- or closed-loop fashion. States of the dynamic neurons evolve as x = -ax+bu, where u is the input to a neuron. The output of the dynamic neurons are given by y = λ(x), where λ(.) is a nonlinear function. The Distributed Dynamic Back Propagation (DDBP) technique is used to back propagate the hierarchical-network output errors. This implementation is useful because it yields a common platform on which many identification and control problems can be investigated.",

author = "De, \{Prasanta K.\} and Massoud Amin and Rodin, \{Ervin Y.\}",

year = "1992",

month = dec,

day = "1",

language = "English (US)",

volume = "2",

pages = "97--102",

editor = "C.H. Dagli and L.I. Burke and Y.C. Shin",

booktitle = "Intelligent Engineering Systems Through Artificial Neural Networks",

publisher = "ASME",

note = "Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 ; Conference date: 15-11-1992 Through 18-11-1992",

}

TY - GEN

T1 - System identification with dynamic neural networks

AU - De, Prasanta K.

AU - Amin, Massoud

AU - Rodin, Ervin Y.

PY - 1992/12/1

Y1 - 1992/12/1

N2 - The application of dynamic neurons to system identification is investigated. Similar networks can easily be extended to the control of systems in an open- or closed-loop fashion. States of the dynamic neurons evolve as x = -ax+bu, where u is the input to a neuron. The output of the dynamic neurons are given by y = λ(x), where λ(.) is a nonlinear function. The Distributed Dynamic Back Propagation (DDBP) technique is used to back propagate the hierarchical-network output errors. This implementation is useful because it yields a common platform on which many identification and control problems can be investigated.

AB - The application of dynamic neurons to system identification is investigated. Similar networks can easily be extended to the control of systems in an open- or closed-loop fashion. States of the dynamic neurons evolve as x = -ax+bu, where u is the input to a neuron. The output of the dynamic neurons are given by y = λ(x), where λ(.) is a nonlinear function. The Distributed Dynamic Back Propagation (DDBP) technique is used to back propagate the hierarchical-network output errors. This implementation is useful because it yields a common platform on which many identification and control problems can be investigated.

UR - https://www.scopus.com/pages/publications/0027105432

UR - https://www.scopus.com/pages/publications/0027105432#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:0027105432

VL - 2

SP - 97

EP - 102

BT - Intelligent Engineering Systems Through Artificial Neural Networks

A2 - Dagli, C.H.

A2 - Burke, L.I.

A2 - Shin, Y.C.

PB - ASME

T2 - Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92

Y2 - 15 November 1992 through 18 November 1992

ER -

System identification with dynamic neural networks

Abstract

Other

Find It

Other files and links

Fingerprint

Cite this