Group of Continuous Time Recurrent Neural Networks

Neeraj Sahu; Adwitiya Sinha

JOURNAL ARTICLE

Group of Continuous Time Recurrent Neural Networks

Year: 2012 Journal: International Journal of Advanced Research in Computer Science Vol: 3 (3)Pages: 622-625 Publisher: International Journal of Advanced Research in Computer Science

Get Full-Text PDF Get Analytical Report

Abstract

This paper explain a different type process for absolute exponential stability (AEST) of a group of continuous time recurrent neural networks with locally Lipschitz continuous and monotone non decreasing activation function. The result extends and improves the existing the analysis of absolute stability (ABST) and absolute exponential stability (AEST). Keywords: Neural network; absolute exponential stability; global exponentially stability.

Keywords:

Lipschitz continuity Monotone polygon Exponential stability Stability (learning theory) Artificial neural network Computer science Activation function Exponential function Exponential growth Applied mathematics Mathematics Mathematical analysis Artificial intelligence Nonlinear system Machine learning Physics

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.35

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Neural Networks and Applications

Physical Sciences → Computer Science → Artificial Intelligence

Group of Continuous Time Recurrent Neural Networks

Abstract

Metrics

Topics

Related Documents

Continuous attractors of discrete-time recurrent neural networks

Self-Optimization in Continuous-Time Recurrent Neural Networks

Adaptive and Variational Continuous Time Recurrent Neural Networks

Other Models of Continuous Time Recurrent Neural Networks

Complete controllability of continuous-time recurrent neural networks