A time decoding realization with a CNN

Aurel A. Lazar, T. Roska, Erno K. Simonyi, L. Tóth

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Time encoding is a novel real-time asynchronous mechanism for encoding amplitude information into a time sequence. The analog bandlimited input is fed into a simple nonlinear neuron-like circuit that generates a strictly increasing time sequence based on which the signal can be reconstructed. The heart of the reconstruction is solving a system of ill-conditioned linear equations. This contribution shows that the equations can be manipulated so that the reconstruction becomes feasible using a Cellular Neural Network (CNN) with a banded system matrix. In particular, the system is first transformed into a well-conditioned smaller system; and then, the Lanczos process is used to lay it out into a set of even smaller systems characterized by a set of tridiagonal matrices. Each of these systems can directly be solved by CNNs, whereas the preprocessing (transformation and Lanczos algorithm) and simple postprocessing phases can be partly or fully implemented by using the digital capabilities of the CNN Universal Machine (CNN-UM). Each step of the proposed formulation is confirmed by numerical (digital) simulations.

Original languageEnglish
Title of host publication2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004
EditorsB. Reljin, S. Stankovic
Pages97-102
Number of pages6
Publication statusPublished - 2004
Event2004 Seventh Seminar on Neural Network Applications in Elecrtical Engineering, NEUREL 2004 - Belgrade
Duration: Sep 23 2004Sep 25 2004

Other

Other2004 Seventh Seminar on Neural Network Applications in Elecrtical Engineering, NEUREL 2004
CityBelgrade
Period9/23/049/25/04

Fingerprint

Cellular neural networks
Decoding
Linear equations
Neurons
Networks (circuits)

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Lazar, A. A., Roska, T., Simonyi, E. K., & Tóth, L. (2004). A time decoding realization with a CNN. In B. Reljin, & S. Stankovic (Eds.), 2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004 (pp. 97-102)

A time decoding realization with a CNN. / Lazar, Aurel A.; Roska, T.; Simonyi, Erno K.; Tóth, L.

2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004. ed. / B. Reljin; S. Stankovic. 2004. p. 97-102.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lazar, AA, Roska, T, Simonyi, EK & Tóth, L 2004, A time decoding realization with a CNN. in B Reljin & S Stankovic (eds), 2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004. pp. 97-102, 2004 Seventh Seminar on Neural Network Applications in Elecrtical Engineering, NEUREL 2004, Belgrade, 9/23/04.
Lazar AA, Roska T, Simonyi EK, Tóth L. A time decoding realization with a CNN. In Reljin B, Stankovic S, editors, 2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004. 2004. p. 97-102
Lazar, Aurel A. ; Roska, T. ; Simonyi, Erno K. ; Tóth, L. / A time decoding realization with a CNN. 2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004. editor / B. Reljin ; S. Stankovic. 2004. pp. 97-102
@inproceedings{553e305585a24748b27e16ee46f42bfc,
title = "A time decoding realization with a CNN",
abstract = "Time encoding is a novel real-time asynchronous mechanism for encoding amplitude information into a time sequence. The analog bandlimited input is fed into a simple nonlinear neuron-like circuit that generates a strictly increasing time sequence based on which the signal can be reconstructed. The heart of the reconstruction is solving a system of ill-conditioned linear equations. This contribution shows that the equations can be manipulated so that the reconstruction becomes feasible using a Cellular Neural Network (CNN) with a banded system matrix. In particular, the system is first transformed into a well-conditioned smaller system; and then, the Lanczos process is used to lay it out into a set of even smaller systems characterized by a set of tridiagonal matrices. Each of these systems can directly be solved by CNNs, whereas the preprocessing (transformation and Lanczos algorithm) and simple postprocessing phases can be partly or fully implemented by using the digital capabilities of the CNN Universal Machine (CNN-UM). Each step of the proposed formulation is confirmed by numerical (digital) simulations.",
author = "Lazar, {Aurel A.} and T. Roska and Simonyi, {Erno K.} and L. T{\'o}th",
year = "2004",
language = "English",
isbn = "0780385470",
pages = "97--102",
editor = "B. Reljin and S. Stankovic",
booktitle = "2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004",

}

TY - GEN

T1 - A time decoding realization with a CNN

AU - Lazar, Aurel A.

AU - Roska, T.

AU - Simonyi, Erno K.

AU - Tóth, L.

PY - 2004

Y1 - 2004

N2 - Time encoding is a novel real-time asynchronous mechanism for encoding amplitude information into a time sequence. The analog bandlimited input is fed into a simple nonlinear neuron-like circuit that generates a strictly increasing time sequence based on which the signal can be reconstructed. The heart of the reconstruction is solving a system of ill-conditioned linear equations. This contribution shows that the equations can be manipulated so that the reconstruction becomes feasible using a Cellular Neural Network (CNN) with a banded system matrix. In particular, the system is first transformed into a well-conditioned smaller system; and then, the Lanczos process is used to lay it out into a set of even smaller systems characterized by a set of tridiagonal matrices. Each of these systems can directly be solved by CNNs, whereas the preprocessing (transformation and Lanczos algorithm) and simple postprocessing phases can be partly or fully implemented by using the digital capabilities of the CNN Universal Machine (CNN-UM). Each step of the proposed formulation is confirmed by numerical (digital) simulations.

AB - Time encoding is a novel real-time asynchronous mechanism for encoding amplitude information into a time sequence. The analog bandlimited input is fed into a simple nonlinear neuron-like circuit that generates a strictly increasing time sequence based on which the signal can be reconstructed. The heart of the reconstruction is solving a system of ill-conditioned linear equations. This contribution shows that the equations can be manipulated so that the reconstruction becomes feasible using a Cellular Neural Network (CNN) with a banded system matrix. In particular, the system is first transformed into a well-conditioned smaller system; and then, the Lanczos process is used to lay it out into a set of even smaller systems characterized by a set of tridiagonal matrices. Each of these systems can directly be solved by CNNs, whereas the preprocessing (transformation and Lanczos algorithm) and simple postprocessing phases can be partly or fully implemented by using the digital capabilities of the CNN Universal Machine (CNN-UM). Each step of the proposed formulation is confirmed by numerical (digital) simulations.

UR - http://www.scopus.com/inward/record.url?scp=20844438029&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20844438029&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:20844438029

SN - 0780385470

SP - 97

EP - 102

BT - 2004 Seventh Seminar on Neural Network Applications in Electrical Engineering - Proceedings, NEUREL 2004

A2 - Reljin, B.

A2 - Stankovic, S.

ER -