Mở rộng cấu trúc và hàm Liapunov cho mạng nơ ron Hopfield

Nguyễn Quang Hoan

Abstract


The existence  the Hopfield neural network and the Liapunov function guarantees the convergence to some local minimum of these network with linear inputs [1,6]. But standard Hopfield architecture [3, 14] is limited in its  capacity of linear classifiers with higher performances. We also regarded some assumptions on these architectures and the their stability.


Refbacks

  • There are currently no refbacks.


Journal of Computer Science and Cybernetics ISSN: 1813-9663

Published by Vietnam Academy of Science and Technology