Optimization of CNN template robustness

Martin Hänggi; George S. Moschytz

Optimization of CNN template robustness

Martin Hänggi, George S. Moschytz

Swiss Federal Institute of Technology Zurich

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

The robustness of a template set for cellular neural networks (CNNs) is crucial for applications of VLSI CNN chips. Whereas the problem of designing any, possibly very sensitive, templates for a given task is fairly easy to solve, it is computationally expensive to find optimal solutions. For the class of bipolar CNNs, we propose an analytical approach to derive the optimally robust template set from any correctly operating template. Furthermore, our method yields a theoretical upper bound for the robustness of the CNN task.

Original language	English
Pages (from-to)	1897-1899
Number of pages	3
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E82-A
Issue number	9
State	Published - 1999
Externally published	Yes

Keywords

Cellular neural networks
Robustness

Cite this

@article{f61614d9041944a393934acd1a2a12aa,

title = "Optimization of CNN template robustness",

abstract = "The robustness of a template set for cellular neural networks (CNNs) is crucial for applications of VLSI CNN chips. Whereas the problem of designing any, possibly very sensitive, templates for a given task is fairly easy to solve, it is computationally expensive to find optimal solutions. For the class of bipolar CNNs, we propose an analytical approach to derive the optimally robust template set from any correctly operating template. Furthermore, our method yields a theoretical upper bound for the robustness of the CNN task.",

keywords = "Cellular neural networks, Robustness",

author = "Martin H{\"a}nggi and Moschytz, {George S.}",

year = "1999",

language = "אנגלית",

volume = "E82-A",

pages = "1897--1899",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "9",

}

TY - JOUR

T1 - Optimization of CNN template robustness

AU - Hänggi, Martin

AU - Moschytz, George S.

PY - 1999

Y1 - 1999

N2 - The robustness of a template set for cellular neural networks (CNNs) is crucial for applications of VLSI CNN chips. Whereas the problem of designing any, possibly very sensitive, templates for a given task is fairly easy to solve, it is computationally expensive to find optimal solutions. For the class of bipolar CNNs, we propose an analytical approach to derive the optimally robust template set from any correctly operating template. Furthermore, our method yields a theoretical upper bound for the robustness of the CNN task.

AB - The robustness of a template set for cellular neural networks (CNNs) is crucial for applications of VLSI CNN chips. Whereas the problem of designing any, possibly very sensitive, templates for a given task is fairly easy to solve, it is computationally expensive to find optimal solutions. For the class of bipolar CNNs, we propose an analytical approach to derive the optimally robust template set from any correctly operating template. Furthermore, our method yields a theoretical upper bound for the robustness of the CNN task.

KW - Cellular neural networks

KW - Robustness

UR - http://www.scopus.com/inward/record.url?scp=0033185149&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0033185149

SN - 0916-8508

VL - E82-A

SP - 1897

EP - 1899

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 9

ER -

Optimization of CNN template robustness

Abstract

Keywords

Other files and links

Fingerprint

Cite this