http:^^www-cse.ucsd.edu^users^crosin^
来自「This data set contains WWW-pages collect」· EDU^USERS^CROSIN^ 代码 · 共 100 行
EDU^USERS^CROSIN^
100 行
Date: Thu, 21 Nov 1996 23:05:01 GMTServer: NCSA/1.4.2Content-type: text/htmlLast-modified: Fri, 27 Sep 1996 09:08:05 GMTContent-length: 2701<TITLE>Chris Rosin's Homepage</TITLE><BODY text=#000000 bgcolor=#bfbfbf><H1> Chris Rosin</H1><HR><PRE>UCSD CSE 0114La Jolla, CA 92093-0114Office: 5402 AP&ME-Mail: crosin@cs.ucsd.edu</PRE><HR><H1>Interests</H1><UL>Genetic algorithms, coevolution, game learning, computational learning theory,neural networks, cellular automata, computational biology.</UL><H1>Current Research</H1><UL>For many problems, performance of candidate solutions needs to be measuredon a suite of test cases. The choice of test cases can be an important factorin the quality of solutions found. <I>Adversarial problems</I> are those for which it is possible to search for good test cases as well as good solutions.Examples include games (strategies must be tested against strong opponents),controller design (test against difficult plants), and grammar induction(test on strings that reveal unusual features of the language). I am exploring theoretical aspects of adversarial problems, and heuristic methodsfor solving them.</UL><H2>Papers</H2> <UL> <LI> Technical Report #CS96-491: <!WA0><A HREF="http://www-cse.ucsd.edu/users/crosin/newmethods.ps">"New methods for Competitive Coevolution"</A>,Christopher D. Rosin and Richard K. Belew.<LI> ICGA 95 paper (submitted version): Two new methods are used to improve theperformance of competitive co-evolution on several games, including Go.<!WA1><A HREF="http://www-cse.ucsd.edu/users/crosin/icgawww.ps">"Methods for Competitive Co-evolution: FindingOpponents Worth Beating"</A>, Christopher D. Rosin and RichardK. Belew. Final version in <I>Proceedings of the Sixth InternationalConference on Genetic Algorithms</I>. L.J. Eshelman, editor.<LI>COLT 96 paper (submitted version): A computational learning theoretic model of game learning is described, and sufficient conditions are givenfor polynomial-time learnability of perfect strategies.<!WA2><A HREF="http://www-cse.ucsd.edu/users/crosin/coltwww.ps">"A Competitive Approach to Game Learning"</A>, ChristopherD. Rosin and Richard K. Belew. Final version in <I>Proceedings of the NinthAnnual ACM Conference on Computational Learning Theory</I>.<LI>An older unpublished extended abstract on <!WA3><A HREF="http://www-cse.ucsd.edu/users/crosin/aaai.ps">Competitive Learning</A>, a theoretical model of learningin a competitive environment.<LI> E. Niebur, C. Koch, and C. Rosin. "An oscillation-based model for the neuronal basis of attention." <I>Vision Research</I> 33:18 (1993).</UL><H2>Links</H2><UL><LI><!WA4><A HREF="http://forum.swarthmore.edu/~jay/learn-game/index.html">Machine Learning in Games</A><LI><!WA5><A HREF="http://www.fusebox.com/cb/alife.html">Live Alife Page</A><LI><!WA6><A HREF="http://www.mth.kcl.ac.uk/~mreiss/compgo.html">Computer Go</A></UL>Whozis?<!WA7><IMG ALIGN=bottom SRC="http://www-cse.ucsd.edu/users/crosin/whozis.gif"></BODY>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?