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
Neste relatório é descrito um método de projeto de redes neurais para gerador de ciclo limite. Primeiro, as condições de restrição para os pesos sinápticos, que são dadas pelas desigualdades lineares, são derivadas da dinâmica das redes neurais. A seguir, as desigualdades lineares são resolvidas pelo método de programação linear. Os pesos sinápticos e outros parâmetros são determinados pelas soluções acima. Além disso, o gerador de ciclo limite baseado em neuro é projetado com circuitos eletrônicos analógicos e simulado pelo Spice. Finalmente, confirmamos que nosso método de projeto é eficiente e prático para o projeto de gerador de ciclo limite baseado em neuro.
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
Teru YONEYAMA, Hiroshi NINOMIYA, Hideki ASAI, "Design Method of Neural Networks for Limit Cycle Generator by Linear Programming" in IEICE TRANSACTIONS on Fundamentals,
vol. E84-A, no. 2, pp. 688-692, February 2001, doi: .
Abstract: In this report, a design method of neural networks for limit cycle generator is described. First, the constraint conditions for the synaptic weights, which are given by the linear inequalities, are derived from the dynamics of neural networks. Next, the linear inequalities are solved by the linear programming method. The synaptic weights and other parameters are determined by the above solutions. Furthermore, neuro-based limit cycle generator is designed with analog electronic circuits and simulated by Spice. Finally, we confirm that our design method is efficient and practical for the design of neuro-based limit cycle generator.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e84-a_2_688/_p
Copiar
@ARTICLE{e84-a_2_688,
author={Teru YONEYAMA, Hiroshi NINOMIYA, Hideki ASAI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Design Method of Neural Networks for Limit Cycle Generator by Linear Programming},
year={2001},
volume={E84-A},
number={2},
pages={688-692},
abstract={In this report, a design method of neural networks for limit cycle generator is described. First, the constraint conditions for the synaptic weights, which are given by the linear inequalities, are derived from the dynamics of neural networks. Next, the linear inequalities are solved by the linear programming method. The synaptic weights and other parameters are determined by the above solutions. Furthermore, neuro-based limit cycle generator is designed with analog electronic circuits and simulated by Spice. Finally, we confirm that our design method is efficient and practical for the design of neuro-based limit cycle generator.},
keywords={},
doi={},
ISSN={},
month={February},}
Copiar
TY - JOUR
TI - Design Method of Neural Networks for Limit Cycle Generator by Linear Programming
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 688
EP - 692
AU - Teru YONEYAMA
AU - Hiroshi NINOMIYA
AU - Hideki ASAI
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E84-A
IS - 2
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - February 2001
AB - In this report, a design method of neural networks for limit cycle generator is described. First, the constraint conditions for the synaptic weights, which are given by the linear inequalities, are derived from the dynamics of neural networks. Next, the linear inequalities are solved by the linear programming method. The synaptic weights and other parameters are determined by the above solutions. Furthermore, neuro-based limit cycle generator is designed with analog electronic circuits and simulated by Spice. Finally, we confirm that our design method is efficient and practical for the design of neuro-based limit cycle generator.
ER -