Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions

Authors:
Gang Bao;Zhigang Zeng
Affiliations:
Department of Control Science and Engineering, Huazhong University of Science and Technology, Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan, Hube ...;Department of Control Science and Engineering, Huazhong University of Science and Technology, Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan, Hube ...
Venue:
Neurocomputing
Year:
2012

Citing 18
Cited 8

A synthesis procedure for associative memories based on space-varying cellular neural networks

Neural Networks
Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions

Neural Computation
Multiperiodicity and Exponential Attractivity Evoked by Periodic External Inputs in Delayed Cellular Neural Networks

Neural Computation
M-matrices and global convergence of discontinuous neural networks: Research Articles

International Journal of Circuit Theory and Applications
Analysis and Design of Associative Memories Based on Recurrent Neural Networks with Linear Saturation Activation Functions and Time-Varying Delays

Neural Computation
Exponential stability of recurrent neural networks with both time-varying delays and general activation functions via LMI approach

Neurocomputing
Novel delay-dependent criteria for global robust exponential stability of delayed cellular neural networks with norm-bounded uncertainties

Neurocomputing
Design of associative memories using cellular neural networks

Neurocomputing
Block attractor in spatially organized neural networks

Neurocomputing
Some multistability properties of bidirectional associative memory recurrent neural networks with unsaturating piecewise linear transfer functions

Neurocomputing
Global asymptotic stability of delayed neural networks with discontinuous neuron activations

Neurocomputing
Global asymptotic stability and robust stability of a class of Cohen-Grossberg neural networks with mixed delays

IEEE Transactions on Circuits and Systems Part I: Regular Papers
Multistability and new attraction basins of almost-periodic solutions of delayed neural networks

IEEE Transactions on Neural Networks
Nontrivial global attractors in 2-D multistable attractor neural networks

IEEE Transactions on Neural Networks
Multistability of recurrent neural networks with time-varying delays and the piecewise linear activation function

IEEE Transactions on Neural Networks
Less conservative results of state estimation for delayed neural networks with fewer LMI variables

Neurocomputing
A new synthesis approach for feedback neural networks based on the perceptron training algorithm

IEEE Transactions on Neural Networks
Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain

IEEE Transactions on Neural Networks

Dynamics Analysis of a Class of Memristor-Based Recurrent Networks with Time-Varying Delays in the Presence of Strong External Stimuli

Neural Processing Letters
Letters: Robustness analysis for connection weight matrix of global exponential stability recurrent neural networks

Neurocomputing
Dynamical analysis on the multistability of high-order neural networks

Neurocomputing
Robustness analysis for connection weight matrices of global exponential stable time varying delayed recurrent neural networks

Neurocomputing
Multistability and instability of delayed competitive neural networks with nondecreasing piecewise linear activation functions

Neurocomputing
Non-typical multistability in neural networks with distributed delays

Neurocomputing
A 3D undulatory locomotion model inspired by C. elegans through DNN approach

Neurocomputing
From different ZFs to different ZNN models accelerated via Li activation functions to finite-time convergence for time-varying matrix pseudoinversion

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper considers a recurrent neural network (RNN) with a special class of discontinuous activation function which is piecewise constants in the state space. One sufficient condition is established to ensure that the novel recurrent neural networks can have (4k-1)^n locally exponential stable equilibrium points. Such RNN is suitable for synthesizing high-capacity associative memories. The design procedure is presented with the method of singular value decomposition. Finally, the validity and performance of the results are illustrated by use of two numerical examples.