Text full multimedia monochrome

First time here?

Find out more about how The Lecture List works.

Coronavirus situation update

Our lecture organisers may or may not have had time to update their events with cancellation notices. Clearly social gatherings are to be avoided and that includes lectures. STAY AT HOME FOLKS, PLEASE.


Find out what you can do to keep The Lecture List online

Stochastic neural networks of the Hopfield type.

A stochastic retarded differential model for continuous-time, random, delayed NNs is related to the CAM dynamic of Cohen, Grossberg and Hopfield.

The asymptotic dynamical behaviour of continuous-time neural networks has been closely studied since the early 1980s. Only recently however have stochastic models (Ito diffusions) of such networks been studied in any detail. Such models allow one to study the effect of random environmental noise (for example, heat) on the dynamics; we may also incorporate delays due to the finite accumulation time of synaptic charges (Hopfield's "short term average") and we attempt to understand the effect of these disturbances on the dynamics.

This talk will present a stochastic retarded differential equation model for continuous-time, random, delayed neural networks. We will present some new work on the Content Addressable Memory dynamic of Cohen, Grossberg and Hopfield and the dynamic of global convergence, which attempts to answer the question: will such dynamical behaviour survive random, delayed disturbances?


Dr Mark Joy | talks | www


Date and Time:

23 February 2005 at 1:30 pm


1 hour



School of Maths, Kingston University
School of Maths, Kingston University
Penrhyn Road
Kingston upon Thames
+44 20 8547 7922

More at School of Maths, Kingston University...




Available from:

Additional Information:

Research seminars are usually held in the Penrhyn Road building of Kingston University. Check the web site for full details and room information.

Register to tell a friend about this lecture.


If you would like to comment about this lecture, please register here.


Any ad revenue is entirely reinvested into the Lecture List's operating fund