IEEE Transactions on Neural Networks and Learning Systems · 2018 · 71 citations · 53 references
Natural SciencesElectrical EngineeringMathematicsComplex SystemsComputational NeuroscienceDynamical SystemsControl TheoryNetwork RobustnessNetwork StabilityNeural NetworksNeuronal DynamicsSpiking Neural NetworksActivation FunctionsContraction Mapping PrincipleEquilibriumNeural DynamicsNeuronal Network DynamicsState-dependent Switching ModelsSwitched SystemsSwitching Systems
This paper is concerned with the multistability of switched neural networks with piecewise linear activation functions under state-dependent switching. Under some reasonable assumptions on the switching threshold and activation functions, by using the state-space decomposition method, contraction mapping theorem, and strictly diagonally dominant matrix theory, we can characterize the number of equilibria as well as analyze the stability/instability of the equilibria. More interesting, we can find that the switching threshold plays an important role for stable equilibria in the unsaturation regions of activation functions, and the number of stable equilibria of an n-neuron switched neural network with state-dependent parameters increases to 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sup> from 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sup> in the conventional one. Furthermore, for two-neuron switched neural networks, the precise attraction basin of each stable equilibrium point can be figured out, and its boundary is composed of the stable manifolds of unstable equilibrium points and the switching lines. Two simulation examples are discussed in detail to substantiate the effectiveness of the theoretical analysis.
53
Cellular neural networks: theory
Leon O. Chua, L. Yang · IEEE Transactions on Circuits and Systems · 1988 · 4.8K citations
Associative memory with nonmonotone dynamics
Masahiko Morita · Neural Networks · 1993 · 371 citations