Discrete-time versus continuous-time models of neural networks

DOI10.1016/0022-0000(92)90038-KzbMath0760.92001MaRDI QIDQ1198658

Edward K. Blum, Xin Wang

Publication date: 16 January 1993

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

zbMATH Keywords

asymptotic consistencynumerical analysisdiscrete-time modelscontinuous-time modelsautonomous systemcirculant networksfeedforward networkssymmetric networksanti-symmetric networks

Mathematics Subject Classification ID

Related Items (13)

Stability of artificial neural networks with impulses ⋮ Extreme stability and almost periodicity in continuous and discrete neuronal models with finite delays ⋮ On a model of competition in periodic environments ⋮ Local lateral inhibition: A key to spike synchronization? ⋮ Delay induced periodicity in a neural netlet of excitation and inhibition ⋮ ON PERIODIC SOLUTIONS OF A TWO-NEURON NETWORK SYSTEM WITH SIGMOIDAL ACTIVATION FUNCTIONS ⋮ Chaotic neural nets, computability, and undecidability: Toward a computational dynamics ⋮ Remote synchronization of amplitudes across an experimental ring of non-linear oscillators ⋮ Convergence analysis of the weighted state space search algorithm for recurrent neural networks ⋮ Exponential stability preservation in discrete-time analogues of artificial neural networks with distributed delays ⋮ Computer simulations of exponentially convergent networks with large impulses ⋮ Exponential stability preservation in semi-discretisations of BAM networks with nonlinear impulses ⋮ Consistency of local dynamics and bifurcation of continuous-time dynamical systems and their numerical discretizations

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mathematical aspects of outer-product asynchronous content-addressable memories
• Nonlinear oscillations, dynamical systems, and bifurcations of vector fields
• On the stochastic dynamics of neuronal interaction
• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• A Unified Approach to Spurious Solutions Introduced by Time Discretisation. Part I: Basic Theory
• SATURATED OUTPUTS FOR HIGH-GAIN, SELF-EXCITING NETWORKS
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.
• Characteristics of Random Nets of Analog Neuron-Like Elements

This page was built for publication: Discrete-time versus continuous-time models of neural networks