Skip to content
Research Article Open access CC BY 3.0

Haraux Type Activation Functions in Neural Network Theory

Nasser-eddine Tatar

Journal of Advances in Mathematics and Computer Science · pp. 3163–3170 · Published 4 Sep 2014

10.9734/BJMCS/2014/12361

Abstract

A general system of ordinary differential equations that appear in neural network theory is studied. We consider nonlinear activation functions which have not been treated in the literature so far. Namely, we assume that the nonlinear activation functions are continuous functions but not necessarily Lipschitz continuous.

Neural network activation function Lipschitz continuous exponential convergence global existence.

References (13)

  1. 1 Computing with Neural Circuits: A Model [DOI]
  2. 2 New conditions for global stability of neural networks with application to linear and quadratic programming problems [DOI]
  3. 3 Global convergence of neural networks with discontinuous neuron activations [DOI]
  4. 4 Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations [DOI]
  5. 5 Nonlinear Evolution Equations — Global Behavior of Solutions [DOI]
  6. 6 Robust State Estimation for Neural Networks With Discontinuous Activations [DOI]
  7. 7 Stability of a class of nonreciprocal cellular neural networks [DOI]
  8. 8 Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions [DOI]
  9. 9 Global asymptotic stability of neural networks with discontinuous activations [DOI]
  10. 10 Stability analysis for neural networks with inverse Lipschitzian neuron activations and impulses [DOI]
  11. 11 Exponential stability and a systematic synthesis of a neural network for quadratic minimization [DOI]
  12. 12 Hopfield Neural Networks with Unbounded Monotone Activation Functions [DOI]
  13. 13 Control of systems with Holder continuous functions in the distributed delays [DOI]

Cited by 7

A nonlinear version of the distributed Halanay inequality and its application

Nasser‐eddine Tatar, Rathinasamy Sakthivel · Mathematical Methods in the Applied Sciences · 2021

Time‐dependent neural networks with activation functions violating the standard Lipschitz condition

Nasser‐eddine Tatar, Sakthivel Rathinasamy · Mathematical Methods in the Applied Sciences · 2022

Asymptotic behavior of a BAM neural network with delays of distributed type

S. Othmani, N.-E. Tatar, A. Khemmoudj · Mathematical Modelling of Natural Phenomena · 2021

Showing 3 of 7 known citations — external sources report more than can currently be individually listed.

Article metrics

Real usage data collected on this platform.

5

Page views

0

PDF downloads

7

Outbound clicks

7

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.