Necessary and sufficient condition for multistability of neural networks evolving on a closed hypercube

نویسندگان

  • Mauro Di Marco
  • Mauro Forti
  • Massimo Grazzini
  • Luca Pancioni
چکیده

The paper considers nonsmooth neural networks described by a class of differential inclusions termed differential variational inequalities (DVIs). The DVIs include the relevant class of neural networks, introduced by Li, Michel and Porod, described by linear systems evolving in a closed hypercube of R(n). The main result in the paper is a necessary and sufficient condition for multistability of DVIs with nonsymmetric and cooperative (nonnegative) interconnections between neurons. The condition is easily checkable and provides a sharp bound between DVIs that can store multiple patterns, as asymptotically stable equilibria, and those for which this is not possible. Numerical examples and simulations are presented to confirm and illustrate the theoretic findings.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

FINITE-TIME PASSIVITY OF DISCRETE-TIME T-S FUZZY NEURAL NETWORKS WITH TIME-VARYING DELAYS

This paper focuses on the problem of finite-time boundedness and finite-time passivity of discrete-time T-S fuzzy neural networks with time-varying delays. A suitable Lyapunov--Krasovskii functional(LKF) is established to derive sufficient condition for finite-time passivity of discrete-time T-S fuzzy neural networks. The dynamical system is transformed into a T-S fuzzy model with uncertain par...

متن کامل

Asymptotic stability of systems operating on a closed hypercube

Sufficient conditions for the global asymptotic stability of the equilibrium x e = 0 of dynamical systems which are characterized by linear ordinary differential equations with saturation nonlinearities are established. The class of systems considered herein arises in the modeling of control systems and neural networks.

متن کامل

Optimum Designing of Forging Preform Die for the H-shaped Parts Using Backward Deformation Method and Neural Networks Algorithm

In a closed die forging process, it is impossible to form complex shapes in one stage, and thus it becomes necessary to use preform dies. In the present study, Backward Deformation Method and FE simulation via ABAQUS software has been used in order to design preform die of the H-shaped parts. In the Backward Deformation Method, the final shape of the part is considered as a starting point and u...

متن کامل

Hypercube Bivariate-Based Key Management for Wireless Sensor Networks

Wireless sensor networks are composed of very small devices, called sensor nodes,for numerous applications in the environment. In adversarial environments, the securitybecomes a crucial issue in wireless sensor networks (WSNs). There are various securityservices in WSNs such as key management, authentication, and pairwise keyestablishment. Due to some limitations on sensor nodes, the previous k...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Neural networks : the official journal of the International Neural Network Society

دوره 54  شماره 

صفحات  -

تاریخ انتشار 2014