Global Exponential Stability of Learning-Based Fuzzy Networks on Time Scales

Abstract EN

We investigate a class of fuzzy neural networks with Hebbian-type unsupervisedlearning on time scales.

By using Lyapunov functional method, some new sufficient conditions arederived to ensure learning dynamics and exponential stability of fuzzy networks on time scales.

Ourresults are general and can include continuous-time learning-based fuzzy networks and correspondingdiscrete-time analogues.

Moreover, our results reveal some new learning behavior of fuzzy synapseson time scales which are seldom discussed in the literature.