Generalized backpropagation through time for continuous time neural networks and discrete time measurements

Krzysztof Fujarewicz; Adam Galuszka

doi:10.1007/978-3-540-24844-6_24

Generalized backpropagation through time for continuous time neural networks and discrete time measurements

Research output: Contribution to journal › Conference article › peer-review

19 Citations (Scopus)

Abstract

This paper deals with the problem of identification of continuous time dynamic neural networks when the measurements are given only at discrete time moments, not necessarily uniformly distributed. It is shown that the modified adjoint system, generating the gradient of the performance index, is a continuous-time system with jumps of state variables at moments corresponding to moments of measurements.

Original language	English
Pages (from-to)	190-196
Number of pages	7
Journal	Lecture Notes in Computer Science
Volume	3070
DOIs	https://doi.org/10.1007/978-3-540-24844-6_24
Publication status	Published - 2004
Event	7th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2004 - Zakopane, Poland Duration: 7 Jun 2004 → 11 Jun 2004

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-540-24844-6_24

Cite this

@article{af9a5b8668fd40e0b99f828069f886ab,

title = "Generalized backpropagation through time for continuous time neural networks and discrete time measurements",

abstract = "This paper deals with the problem of identification of continuous time dynamic neural networks when the measurements are given only at discrete time moments, not necessarily uniformly distributed. It is shown that the modified adjoint system, generating the gradient of the performance index, is a continuous-time system with jumps of state variables at moments corresponding to moments of measurements.",

author = "Krzysztof Fujarewicz and Adam Galuszka",

year = "2004",

doi = "10.1007/978-3-540-24844-6\_24",

language = "English",

volume = "3070",

pages = "190--196",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Science and Business Media Deutschland GmbH",

note = "7th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2004 ; Conference date: 07-06-2004 Through 11-06-2004",

}

TY - JOUR

T1 - Generalized backpropagation through time for continuous time neural networks and discrete time measurements

AU - Fujarewicz, Krzysztof

AU - Galuszka, Adam

PY - 2004

Y1 - 2004

N2 - This paper deals with the problem of identification of continuous time dynamic neural networks when the measurements are given only at discrete time moments, not necessarily uniformly distributed. It is shown that the modified adjoint system, generating the gradient of the performance index, is a continuous-time system with jumps of state variables at moments corresponding to moments of measurements.

AB - This paper deals with the problem of identification of continuous time dynamic neural networks when the measurements are given only at discrete time moments, not necessarily uniformly distributed. It is shown that the modified adjoint system, generating the gradient of the performance index, is a continuous-time system with jumps of state variables at moments corresponding to moments of measurements.

UR - https://www.scopus.com/pages/publications/9444261975

U2 - 10.1007/978-3-540-24844-6_24

DO - 10.1007/978-3-540-24844-6_24

M3 - Conference article

AN - SCOPUS:9444261975

SN - 0302-9743

VL - 3070

SP - 190

EP - 196

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

T2 - 7th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2004

Y2 - 7 June 2004 through 11 June 2004

ER -

Generalized backpropagation through time for continuous time neural networks and discrete time measurements

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this