Michigan vs. Pitt approach

Michigan vs. Pitt approach

Post by redemptio » Thu, 21 Aug 2003 00:33:40



I know this has been discussed ad nauseum, but I would like to know a good
central place where the Michigan Approach and the Pitt (or Pittsburgh)
approach are compared. Any I've read write on the basic workings and
comparison, but I think these are lacking in depth, because they are often
short accounts of the differences.

I must be missing out on years of debate (between proponents of both
approaches) because what I've found so far seems to miss the depth of the
arguments for and against both approaches and their relative merits.

Thanks.

 
 
 

Michigan vs. Pitt approach

Post by Will Pears » Thu, 28 Aug 2003 07:06:55



> I know this has been discussed ad nauseum, but I would like to know a good
> central place where the Michigan Approach and the Pitt (or Pittsburgh)
> approach are compared. Any I've read write on the basic workings and
> comparison, but I think these are lacking in depth, because they are often
> short accounts of the differences.

> I must be missing out on years of debate (between proponents of both
> approaches) because what I've found so far seems to miss the depth of the
> arguments for and against both approaches and their relative merits.

> Thanks.

I don't know of any centralised place where the Pitt vs Michi approach
is discussed. You might try asking people on comp.ai.genetic

I had some lecturers on LCS by a researcher (Larry Bull) in them and
he was interested in creating new types of LCS or exploring extensions
to simpler LCS systems such as Zeroth Classifier Systems. Which are
based on stripped down michigan style classifier systems.

Another of the things he was interested in was a neural classifier
system. Where the representation was interpreted as a recurrent Neural
net, but searched by a modified genetic algorithm. This can be seen as
a form of Pittsburgh Classifier system as the neural net could
represent many rules and have memory in itself.

So from what I have seen of the LCS community would say the debate has
died down and researchers accepted both have advantages and
disadvantages and use whatever works dependant upon the type of system
they are trying to create.

My view on LCS is that it is too restricted in how rules are created
to have much future in general problem solving (my own research I am
slowly trying to cross Pushpop (a form of GP), LCS and Tierra).

 Will Pearson

 
 
 

Michigan vs. Pitt approach

Post by Will Pears » Thu, 28 Aug 2003 07:11:48


In my previous message I got Pittsburgh and Michigan confused. For
some reason I always do this.

Why couldn't they have called them monolithic and decentralised or
some other descriptive term that actually has some bearing on what
they do?

  Will Pearson

 
 
 

1. ISO: Paper on centralized vs. distributed approaches to MAS

Hi,
I'm a grad student currently working in Multi-Agent systems.
I'm looking for a paper that compares centralized approach with
distributed approach.

I remember vagulely having read an article/paper long back in which the
author(s)  argued that theoretically, centralized  approach may have a
better/efficient solution than distributed approach. But in practice we
get a better solution using a distributed approach(ofcourse not true in
all cases).Eg. in domains where no single person/agent has all
information about the current state, and there is inherent noise.
Do we really reach the efficency-levels/profitability/optimality that we
claim that centralized approach brings over distributed approach?
any pointers to research in this direction?
thanks in advance.
Murali.
--
******************

Grad RA, Dept. of CSE,
U of S.Carolina,Columbia.
******************
"What we Are is God's gift to us. What we Become is our gift to God"

[ comp.ai is moderated.  To submit, just post and be patient, or if ]

[ ask your news administrator to fix the problems with your system. ]

2. Printing from 'Domain' Laptop to workgroup PC - Without having to log in locally..

3. Linguistic approaches to AI Linguistic Approaches to Artificial Intelligence

4. Notes.log question

5. US-PA-Pitt: AI Programming (Lisp), Computer-based Learning, LRDC

6. ban web sites ..

7. *** Graduate Program Announcement: AI at Pitt ***

8. Constant Connection

9. ENCORE: New EClair at Michigan State University

10. Q: Getting Univ. of Michigan Technical Report

11. February 10, 1998 Southeast Michigan ACM SIGART (SMART) meeting