Swarms, evolution and all that jazz
Date and time: 11.30am-12.30pm, Friday 7th April, 2006
Venue: 10.08.04
Chair: Xiaodong Li
Abstract:
Collective Intelligence Systems draw their inspiration from biology where a
number of simple units often achieve a performance that is greater than the sum
of their parts because of the way they are organised together. The way that birds flock and perform
efficient searches without any hierarchical organisation structure has inspired
an algorithm called Particle Swarm Optimisation (PSO).
In this talk it will be suggested that traditional PSO
is still too biological and that with the addition of a non-biological feature
and evolution it can be extended to perform efficient searches in highly
complex problem domains. For example, in a problem domain with 10^27 discrete
optima, it has a 40% chance of finding the global optimum with only 1.5*10^7
evaluations. Further more it will find a series of very good optima, not just
one. This obviously has importance when the time taken to evaluate a possible
solution to a problem is long, but the solution is needed fast. Many real world industrial problems have such
constraints.
The seminar will start with the basics of PSO
before moving onto the new algorithm and showing the results on two complex
problem domains. It will conclude with a suggestion (and hopefully preliminary
results) as to how this remarkable performance can be made even better.
About the speaker:
Professor Tim Hendtlass was born
in the UK just
in time to be nearly hit by one of the last V1s of WWII. He did schooling in
the UK before
moving with his family to New Zealand
where he undertook university training, ending up with a PhD in Ionospheric Physics from Massey
University. After this he found a job at RMIT, where for
10 years he taught physics in general and instrumentation in particular. In
1984 he moved to Swinburne with the intention of
being there for five years or so. The ‘or so’ has turned out to be until now
(apart form a sabbatical overseas).
His interests have moved from physics to computing and to
artificial intelligence in particular.
He has produced over 50 refereed publications and supervised some 20
postgraduate research students in the fields of artificial neural networks,
evolutionary systems and, more recently, collective intelligence. He is a
member of a number of professional societies and has been a member of the Board
of Governors of the International Society of Applied Intelligence for the past
10 years.
Seminar Organisation
Seminars are free and open to the general public. No booking is necessary.
If you are interested in giving a presentation in this seminar series, or to
make suggestions for speakers, please contact Xiaodong Li, the seminar
co-ordinator.