barash@mmlai.UUCP (Rev. Steven C. Barash) (05/23/88)
A while back someone posted an extended definition of "Genetic algorithms".
If anyone still has that, or has their own definition, could you please
e-mail it to me? (There's probably lots of room for opinions here;
I'm interested in all perspectives).
I would also appreciate any pointers to literature in this area.
Also, if anyone wants me to post a summary of the replies, let me know.
Thanks in advance!
Steve Barash
--
Steve Barash @ Martin Marietta Labs
ARPA: barash@mmlai.uu.net
UUCP: {uunet, super, hopkins!jhunix} !mmlai!barashbc@mit-amt.MEDIA.MIT.EDU (bill coderre) (05/25/88)
In article <317@mmlai.UUCP> barash@mmlai.UUCP (Rev. Steven C. Barash) writes: >A while back someone posted an extended definition of "Genetic algorithms". >I would also appreciate any pointers to literature in this area. Well, let's start talking about it right here. Make a change from the usual rhetoric. The classic (Holland) Genetic Algorithm stuff involves a pool of rules which look like ascii strings, the left side of which are preconditions and the right which are assertions. Attached to each rule is a probability of firing. When the clock ticks, all the rules that match their left side are culled, and one is probabilistically selected to fire. There is also an "evaluator" that awards "goodness" to rules that are in the chain of producing a good event. This goodness usually results in greater probability of firing. (Of course, one could also use punishment strategies.) Last, there is a "mutator" that makes new rules out of old. Some heuristics that are used: * randomly change a substring (usually one element) * "breed" two rules together, by taking the first N of one and the last M-N of another. The major claim is that this approach avoids straight hill-climbing's tendency to get stuck on local peaks, by using some "wild" mutations, like reversing substrings of rules. I'm not gonna guess whether this claim is true. I have met Stewart Wilson of the Rowland Institute here in Cambridge, and he has made simple critters that use the above strategy. They start out with random rulebases, and over the course of a few million ticks develop optimal ones. >>>>>>>>>> What is particularly of interest to me is genetic-LIKE algorithms that use more sophisticated elements than ascii strings and simple numeric scorings. My master's research is an attempt to extend Genetic AI in just that way. I wanna use genetic AI's ideas to cause a Society of Mind to learn. It appears that using Lenat-like ideas is the right way to make the mutator, but the evaluator seems like a difficult trick. My hunch is to use knowledge frames ala Winston, but this is looking less likely. ?????????? So does anybody know about appropriately similar research? Anybody got any good ideas? appreciamucho....................................................bc
pi@pollux.usc.edu (Bill Pi) (05/30/88)
In article <317@mmlai.UUCP> barash@mmlai.UUCP (Rev. Steven C. Barash) writes: > >A while back someone posted an extended definition of "Genetic algorithms". >If anyone still has that, or has their own definition, could you please >e-mail it to me? (There's probably lots of room for opinions here; >I'm interested in all perspectives). > >I would also appreciate any pointers to literature in this area. Up till now, there are two conferences held already for Genetic Algorithms: Proceeding of the First International Conference on Genetic Algorithms and Their Applications, ed. J. J. Grefenstette, 1985. Genetic Algorithms and Their Applications: Proceeding of the Second Inter- national Conference o Genetic Algorithms, ed. J. J. Grefenstette, 1987. They can be ordered from: Lawrence Erlbaum Associates, Inc. 365 Broadway Hillsdale, NJ 07642 (201) 666-4110 A latest collection of research notes on GA is Genetic Algorithms and Simulated Annealing, ed. L. Davis, 1987, Morgan kaufmann Publishers, Inc., Los Altos, Ca. Also, A mailing list exists for Genetic Algorithms researchers. For more info. send mail to "GA-List-Request@NRL-AIC.ARPA". Jen-I Pi :-) UUCP: {sdcrdcf,cit-cav}!oberon!durga!pi Department of Electrical Engineering CSnet: pi@usc-cse.csnet University of Southern California Bitnet: pi@uscvaxq Los Angeles, Ca. 90089-0781 InterNet: pi%durga.usc.edu@oberon.USC.EDU
androula@cb.ecn.purdue.edu (Ioannis Androulakis) (05/12/89)
I would like to know if there has been any work done, concerning the application of Genetic Algorithms in cases where the search space can not be represented by a prespecified and fixed string length. I am interested in applying GAs in synthesis problems and therfore I would like to have a greater flexibility in the representation. I would appreciate any help. Thank you, yannis androula@helium.ecn.purdue.edu
androula@cb.ecn.purdue.edu (Ioannis Androulakis) (12/21/89)
I would like to implement some sort of pattern
learning in my Genetic Algorithm search. In other
words I would like to exploit the pattern of changes
which cause an imporovement from one generation to another.
I would appreciate any help,
thank you,
Ioannis P. Androulakis
e-mail : androula@lips1.ecn.purdue.edumaddur@ms.uky.edu (Sudarsan K. Maddur) (09/05/90)
I am looking for some references in using Genetic Algorithms for creating the neural network architecture. I am also looking for a paper in which the author(s) discusses different approaches to create neural network architecture using Genetic Algorithms. Thanks in advance, Sudarsan K. Maddur e-mail: maddur@ms.uky.edu
young@cs.umn.edu (Mike Young) (09/07/90)
maddur@ms.uky.edu (Sudarsan K. Maddur) writes: >I am looking for some references in using Genetic Algorithms for creating the >neural network architecture. >I am also looking for a paper in which the author(s) discusses different >approaches to create neural network architecture using Genetic Algorithms. For an excellent overview with plenty of references: Evolving networks: Using the genetic algorithm with connectionist learning. Belew, McInerney and Schraudolph, 1990. UCSD Tech report, CSE Technical Report #CS90-174. I believe I retrieved my copy from ohio state's neuroprose repository. Good luck, Mike Young
simonof@aplcen.apl.jhu.edu (Simonoff Robert 301 540 1864) (12/09/90)
I am interested in any references you all might have seen concerning genetic algorithms used in conjunction with neural networks. Please send to me via e-mail and I will post a summary. Thanks Bob Simonoff -- *********************************************************** Bob Simonoff simonof@aplcen Johns Hopkins University
maurits@Neon.Stanford.EDU (A. Maurits van der Veen) (12/10/90)
In article <1990Dec9.012258.11003@aplcen.apl.jhu.edu> simonof@aplcen (Simonoff Robert 301 540 1864) writes: >I am interested in any references you all might have seen >concerning genetic algorithms used in conjunction with >neural networks. Please send to me via e-mail and I >will post a summary. > >Thanks >Bob Simonoff > (Sorry, I tried e-mail, but was told your host was unknown). Try the following: Dodd, N. (1990). Optimisation of Network Structure using Genetic Techniques. IEEE: Proceedings of the International Joint Conference on Neural Networks, vol. 3, pp. 965-968. San Diego, CA. Harp, S., T. Samad, and A. Guha (1989). Towards the Genetic Synthesis of Neural Networks. Proceedings of the Third International Conference on Genetic Al gorithms.(pp. 360-369). San Mateo, CA: Morgan Kaufmann. Miller, G., P. Todd, and S. Hegde (1989). Designing Neural Networks using Genetic Algorithms. Proceedings of the Third International Conference on Genetic Algorithms (pp. 379-384). That proceedings volume has a whole section on combining GAs and NNs. Besides these three papers, I am aware of a number of papers that deal with using GAs to set the weights in NNs (the three above use them to decide on the topology). A review of some of them, and some more source listings, may be found in: Neural Network, vol. 4, nr. 1, pp. 47-53, which contains 3 reviews or recent work in the area, with responses by the others of the work. Hope this is useful. Maurits van der Veen maurits@cs.stanford.edu
simonof@aplcen.apl.jhu.edu (Simonoff Robert 301 540 1864) (12/10/90)
In article <1990Dec9.184729.21949@Neon.Stanford.EDU> maurits@Neon.Stanford.EDU (A. Maurits van der Veen) writes: >(Sorry, I tried e-mail, but was told your host was unsuccessful). >Maurits van der Veen >maurits@cs.stanford.edu Sorry, my full e-mail address is simonof@aplcen.apl.edu. -- *********************************************************** Bob Simonoff simonof@aplcen Johns Hopkins University
esrmm@warwick.ac.uk (Denis Anthony) (12/11/90)
In article <1990Dec9.012258.11003@aplcen.apl.jhu.edu> simonof@aplcen (Simonoff Robert 301 540 1864) writes: >I am interested in any references you all might have seen >concerning genetic algorithms used in conjunction with >neural networks. Please send to me via e-mail and I >will post a summary. > >Thanks >Bob Simonoff > I tried email unsucessfully, (including the more full email address you gave later). %Q Schaffer J.D, Caruana R.A, and Eshelman L.J %D 1989 %T Using Genetic Search to Exploit the Emergent Behavior of Neural Networks (Technical Report, Phillips Labs, New York) %P 1-8 %L 56 %Q Anthony D.M, Hines E.L, Taylor D, and Barham J %D 1990 %T The Use of Genetic Algorithms to Learn the Most Appropriate Inputs to a Neural Network %J IASTED Conf. Artificial Intelligence App. & Neural Networks %L 169 %Q De Garis H %D 1989 %T WALKER, A Genetically Programmed, Time Dependent, Neural Net Which Teaches a Pair of Sticks to Walk (Technical Report, Center for AI, George Mason Univ, Virginia) %L 32 %Q Whitley D %D 1989 %T Applying Genetic Algorithms to Neural Network Learning (in Proceedings of the 7th Conference of the Society for the Study of Artificial Intelligence and Simulation of Behaviour, ed Cohn A) %J Robotics Neural Networks and Vision %P 137-144 %L 69
mukesh@syma.sussex.ac.uk (Mukesh Patel) (12/13/90)
>In article <1990Dec9.012258.11003@aplcen.apl.jhu.edu> simonof@aplcen (Simonoff Robert 301 540 1864) writes: >>I am interested in any references you all might have seen >>concerning genetic algorithms used in conjunction with >>neural networks. Please send to me via e-mail and I >>will post a summary. >> >>Thanks >>Bob Simonoff (Sorry, I tried e-mail, but was told your host was unknown). A paper by Meyer and Guillot "From Animals to Animats: All you wanted to know about simulation of adaptive behavior" has a number of refs on GA. Let me know if you would like a copy - the paper was presented at the Animals to Animats conference in Paris last summer, and is included in the forthcoming proceedings volume. Mukesh Patel The University of Sussex, School of Cognitive and Computing Sciences, Falmer, Brighton BN1 9QH, UK Phone: +44 273 606755 x3074 JANET:mukesh@uk.ac.sussex.cogs Fax: +44 273 678188 ARPA:mukesh%cogs.sussex.ac.uk@nfsnet-relay.ac.uk