Posted by
Kenneth Lloyd on
Apr 08, 2008; 8:03pm
URL: http://friam.383.s1.nabble.com/Agent-Based-Modeling-s-Role-in-Understanding-Complexity-tp525934p526045.html
Ann,
Are you looking for information on desktop (generally, serial processing or
dual multi-processing, threaded) applications - such as NetLogo or StarLogo?
Or are you looking for information on ABM using MPP (massively parallel
processing) using multiple GPU (graphics cards) for the mathematical vector
and matrix simulations of "intelligent" agents (natural, human or weak
artificial)?
The sigevolution.org site shows how evolutionary genetic algorithms evolve
into patterns (such as swarm behavior, or entangled behavior as ref: in the
Ropella e-mail). Some of this work is from E-Plex and their research into
Complex Pattern Producing Networks (CPPN's)
http://eplex.cs.ucf.edu/.
Do not be mislead by the triviality of their examples - this can be powerful
stuff.
Another place to start is the Swarm wiki
http://www.swarm.org
at the University of Michigan.
The term Agent Based Modeling (ABM) seems to cast a wide net - from "simple"
cellular automata to phenotypical behavior of genotypically evolved and
generated, quasi-intelligent artificial organisms (often referred to as
complex adaptive systems). I guess I would need to know at what level you
wish to understand agent based modeling of complex systems in order to
recommend an executive summary (which may be an oxymoron). By this I mean,
Stephen Wolfram's A New Kind of Science may be considered by some to be an
executive summary on ABM. Specifically see page 991, Implications for
Everyday Systems (Notes for Chapter 8) - Issues of Modeling - which ties up
my recommendations with a pretty bow. This is as close as I could come to
an executive summary.
Referring to your original e-mail, IMO, the Bayesian approach is meaningless
without the application of the Inverse Theory to refine it. I recommend
Scales (see original post), because it is simple, clear, and reachable.
Having said this, I'm afraid I haven't been very helpful.
=============================
Kenneth A. Lloyd
CEO and Director of Systems Science
Watt Systems Technologies Inc.
Albuquerque, NM USA
kalloyd at wattsys.com
kenneth.lloyd at incose.org - MBSE Complex, Adaptive & Stochastic Systems
kenneth.lloyd at nmug.net - Director of Education
www.wattsys.com <
http://www.wattsys.com/>
<
http://www.linkedin.com/pub/7/9a/824>
http://www.linkedin.com/pub/7/9a/824
This e-mail is intended only for the addressee named above. It may contain
privileged or confidential information.
If you are not the addressee you must not copy, distribute, disclose or use
any of the information in it.
If you have received it in error please delete it and immediately notify the
sender.
_____
From:
[hidden email] [mailto:
[hidden email]] On Behalf
Of admin at wkbank.com
Sent: Tuesday, April 08, 2008 12:17 PM
To: 'The Friday Morning Applied Complexity Coffee Group'
Subject: Re: [FRIAM] ABM,Baysian and Monte Carlo Method's Role in
Understanding Complexity
Thank you Ken,
I am wondering though if someone has an executive summary?
Were any of your citations specific agent based models?
_____
From:
[hidden email] [mailto:
[hidden email]] On Behalf
Of Ken Lloyd
Sent: Tuesday, April 08, 2008 10:51 AM
To: 'The Friday Morning Applied Complexity Coffee Group'
Subject: Re: [FRIAM] ABM,Baysian and Monte Carlo Method's Role in
Understanding Complexity
Ann,
Get you pencil and paper ready ...
http://www.sigevolution.org/issues/pdf/SIGEVOlution200702.pdf
Christopher Bishop, Neural Networks for Pattern Recognition, Oxford
University Press, 1995
Klaus Mosegaard - Monte Carlo Analysis of Geophysical Inverse Problems,
http://wwwrses.anu.edu.au/~malcolm/papers/pdf/SamMos02.pdf
Klaus Mosegaard, 1998: Resolution Analysis of General Inverse Problems
through Inverse Monte Carlo Sampling: Inverse Problems 14, pp. 405-426.
James Scales, M. Smith, and S. Treitel, Introductory Geophysical Inverse
Theory, Samizdat Press, Golden, CO USA, 2001,
<
http://acoustics.mines.edu/jscales/gp605/snapshot.pdf>
http://acoustics.mines.edu/jscales/gp605/snapshot.pdf
See the many books and papers by Mosegaard and Tarantola
The network aspects are generally covered in Newman, Barabasi and Watts, The
Structure and Dynamics of Networks, Princeton Series on Complexity
Ken
=============================
Kenneth A. Lloyd
CEO and Director of Systems Science
Watt Systems Technologies Inc.
Albuquerque, NM USA
kalloyd at wattsys.com
kenneth.lloyd at incose.org - MBSE Complex, Adaptive & Stochastic Systems
kenneth.lloyd at nmug.net - Director of Education
www.wattsys.com <
http://www.wattsys.com/>
<
http://www.linkedin.com/pub/7/9a/824>
http://www.linkedin.com/pub/7/9a/824
This e-mail is intended only for the addressee named above. It may contain
privileged or confidential information.
If you are not the addressee you must not copy, distribute, disclose or use
any of the information in it.
If you have received it in error please delete it and immediately notify the
sender.
_____
From:
[hidden email] [mailto:
[hidden email]] On Behalf
Of admin at wkbank.com
Sent: Tuesday, April 08, 2008 10:16 AM
To: 'The Friday Morning Applied Complexity Coffee Group'
Subject: Re: [FRIAM] ABM,Baysian and Monte Carlo Method's Role in
Understanding Complexity
Thanks to all who responded.
"After all, it's the _braided_ or woven nature of causal networks (in
contrast to causal _chains_) that gave rise to ABM to begin with." glen e.
p. ropella
Could you or someone recommend a good ABM (as in the above quotation) that I
might study?
I thought glen's description of bayesian was very clear. Could glen or
someone else give a similarly clear and intuitive description of Bayesian
Monte Carlo or Markov Chain Monte Carlo method?
Ann Racuya-Robbins
World Knowledge BankR A Virtual Democratic Country
www.wkbank.com
============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
lectures, archives, unsubscribe, maps at
http://www.friam.org-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://redfish.com/pipermail/friam_redfish.com/attachments/20080408/2938b695/attachment.html