Mixed analog/digital chaotic neuro-computer prototype: 400-neuron dynamical associative memory

Yoshihiko Horio; Takahide Okuno; Koji Mori

doi:10.1109/IJCNN.2004.1380862

Mixed analog/digital chaotic neuro-computer prototype: 400-neuron dynamical associative memory

Yoshihiko Horio, Takahide Okuno, Koji Mori

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

3 Citations (Scopus)

Abstract

We construct the dynamical associative memory on the switched-capacitor (SC) 400-neuron chaotic neuro-computer prototype. We observe a variety of associative dynamics from the prototype. The chaotic behavior of the dynamical association comes from complexity in real number. The analog SC chaotic neurons used in the system can handle real numbers through their continuous variables, therefore, they would faithfully reproduce the chaotic behavior. In construct, digital computers cannot handle almost all real numbers. In this respect, we analyze the measured results from the hardware system in comparison with those from computer simulations. In the computer simulation, we take into account characteristics of the analog circuit and noise.

Original language	English
Title of host publication	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Pages	1717-1722
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2004.1380862
Publication status	Published - 2004 Dec 1
Externally published	Yes
Event	2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary Duration: 2004 Jul 25 → 2004 Jul 29

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	3
ISSN (Print)	1098-7576

Other

Other	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Country	Hungary
City	Budapest
Period	04/7/25 → 04/7/29

ASJC Scopus subject areas

Software

Access to Document

10.1109/IJCNN.2004.1380862

Fingerprint Dive into the research topics of 'Mixed analog/digital chaotic neuro-computer prototype: 400-neuron dynamical associative memory'. Together they form a unique fingerprint.

Cite this

Horio, Y., Okuno, T., & Mori, K. (2004). Mixed analog/digital chaotic neuro-computer prototype: 400-neuron dynamical associative memory. In 2004 IEEE International Joint Conference on Neural Networks - Proceedings (pp. 1717-1722). (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 3). https://doi.org/10.1109/IJCNN.2004.1380862

Mixed analog/digital chaotic neuro-computer prototype : 400-neuron dynamical associative memory. / Horio, Yoshihiko; Okuno, Takahide; Mori, Koji.

2004 IEEE International Joint Conference on Neural Networks - Proceedings. 2004. p. 1717-1722 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 3).

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

Horio, Y, Okuno, T & Mori, K 2004, Mixed analog/digital chaotic neuro-computer prototype: 400-neuron dynamical associative memory. in 2004 IEEE International Joint Conference on Neural Networks - Proceedings. IEEE International Conference on Neural Networks - Conference Proceedings, vol. 3, pp. 1717-1722, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, Hungary, 04/7/25. https://doi.org/10.1109/IJCNN.2004.1380862

@inproceedings{3cd8f1149a9c44568205441c3f75105f,

title = "Mixed analog/digital chaotic neuro-computer prototype: 400-neuron dynamical associative memory",

abstract = "We construct the dynamical associative memory on the switched-capacitor (SC) 400-neuron chaotic neuro-computer prototype. We observe a variety of associative dynamics from the prototype. The chaotic behavior of the dynamical association comes from complexity in real number. The analog SC chaotic neurons used in the system can handle real numbers through their continuous variables, therefore, they would faithfully reproduce the chaotic behavior. In construct, digital computers cannot handle almost all real numbers. In this respect, we analyze the measured results from the hardware system in comparison with those from computer simulations. In the computer simulation, we take into account characteristics of the analog circuit and noise.",

author = "Yoshihiko Horio and Takahide Okuno and Koji Mori",

year = "2004",

month = dec,

day = "1",

doi = "10.1109/IJCNN.2004.1380862",

language = "English",

isbn = "0780383591",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "1717--1722",

booktitle = "2004 IEEE International Joint Conference on Neural Networks - Proceedings",

note = "2004 IEEE International Joint Conference on Neural Networks - Proceedings ; Conference date: 25-07-2004 Through 29-07-2004",

}

TY - GEN

T1 - Mixed analog/digital chaotic neuro-computer prototype

T2 - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

AU - Horio, Yoshihiko

AU - Okuno, Takahide

AU - Mori, Koji

PY - 2004/12/1

Y1 - 2004/12/1

N2 - We construct the dynamical associative memory on the switched-capacitor (SC) 400-neuron chaotic neuro-computer prototype. We observe a variety of associative dynamics from the prototype. The chaotic behavior of the dynamical association comes from complexity in real number. The analog SC chaotic neurons used in the system can handle real numbers through their continuous variables, therefore, they would faithfully reproduce the chaotic behavior. In construct, digital computers cannot handle almost all real numbers. In this respect, we analyze the measured results from the hardware system in comparison with those from computer simulations. In the computer simulation, we take into account characteristics of the analog circuit and noise.

AB - We construct the dynamical associative memory on the switched-capacitor (SC) 400-neuron chaotic neuro-computer prototype. We observe a variety of associative dynamics from the prototype. The chaotic behavior of the dynamical association comes from complexity in real number. The analog SC chaotic neurons used in the system can handle real numbers through their continuous variables, therefore, they would faithfully reproduce the chaotic behavior. In construct, digital computers cannot handle almost all real numbers. In this respect, we analyze the measured results from the hardware system in comparison with those from computer simulations. In the computer simulation, we take into account characteristics of the analog circuit and noise.

UR - http://www.scopus.com/inward/record.url?scp=10844221590&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10844221590&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2004.1380862

DO - 10.1109/IJCNN.2004.1380862

M3 - Conference contribution

AN - SCOPUS:10844221590

SN - 0780383591

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 1717

EP - 1722

BT - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

Y2 - 25 July 2004 through 29 July 2004

ER -