The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
O robustez de um conjunto de modelos para redes neurais celulares (CNNs) é crucial para aplicações de chips VLSI CNN. Embora o problema de projetar qualquer modelo, possivelmente muito sensível, para uma determinada tarefa seja bastante fácil de resolver, é computacionalmente caro encontrar soluções ótimas. Para a classe de CNNs bipolares, propomos uma abordagem analítica para derivar o conjunto de modelos robustos de qualquer modelo operando corretamente. Além disso, nosso método produz um limite superior teórico para a robustez da tarefa CNN.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Martin HANGGI, George S. MOSCHYTZ, "Optimization of CNN Template Robustness" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 9, pp. 1897-1899, September 1999, doi: .
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.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_9_1897/_p
Copiar
@ARTICLE{e82-a_9_1897,
author={Martin HANGGI, George S. MOSCHYTZ, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Optimization of CNN Template Robustness},
year={1999},
volume={E82-A},
number={9},
pages={1897-1899},
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={},
doi={},
ISSN={},
month={September},}
Copiar
TY - JOUR
TI - Optimization of CNN Template Robustness
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1897
EP - 1899
AU - Martin HANGGI
AU - George S. MOSCHYTZ
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 1999
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.
ER -