📄 http:^^www.cs.wisc.edu^~belew^ccsrg.html
字号:
Date: Tue, 05 Nov 1996 20:39:50 GMTServer: NCSA/1.5Content-type: text/htmlLast-modified: Thu, 04 May 1995 18:17:39 GMTContent-length: 4084<HEAD><TITLE>Cognitive Computer Science Research Group</TITLE></HEAD><BODY><P> <HR> <center><h1>Cognitive Computer Science <BR> Research Group</h1>Computer Science &Engr. Dept. (0114)<BR>University of California - San Diego <BR>La Jolla, CA 92093<BR>April, 1995<BR><P><!WA0><a HREF="http://www.cs.wisc.edu/~belew/research-stmnt.html">Richard K. Belew</a>, Director<BR></center><P><HR><UL><HEAD><P>We are a research group within the AI laboratory. Our name, CCSRG,is meant to indicate that while our approach is primarily <em>computational</em>, we are informed by a <em>cognitive</em>perspective on both artificial and natural systems.<P>The focus of our research group is the characterization of adaptiveknowledge representations. Issues of representation have alwaysplayed a central role in artificial intelligence (AI), as well as incomputer science and theories of mind more generally. We would arguethat most of this work has (implicitly or explicitly) assumed that therepresentational language is wielded <em>manually</em>, by humansencoding an explicit characterization of what they believe to be trueof the world. We believe there are fundamental philosophicaldifficulties inherent in any such approach aside. Further, there nowexist modern machine learning techniques capable of <em>automatically</em> developing elaborate representations of the world. Todate, however, the representations underlying this learning have notshown themselves able to "scale up" to the semantically sophisticatedtask domains often associated with AI expert systems. We believe itis therefore appropriate to reconsider basic notions of what makes forgood knowledge representation, with constraints imposed by thelearning process considered <em>sine qua non</em> but in conjuction withothers (expressive adequacy, valid inference, etc.) more typicallyconsidered by AI.<P>We have found it productive to pursue this general interest through several more specific research projects. The first applies statistical techniques to the problem of free-text information retrieval (IR) and linguistics more generally. Many of our projects use a connectionist (neural network) representation of documents and descriptive keywords that uses relevance feedback as a training signal to a reinforcement learning algorithm. This construction allows an IR system to learn a more effective indexing representation of free-text documents as a simple by-product of the browsing behaviors of its users. Second, we have investigated a wide range of Genetic Algorithm (GAs) applications, ranging from use in "artificial life" models of natural phenomena to use as an artificial inductive method to accomplish an engineering goal like optimizing a function. We believe our work in these two areas allows a ``stereoscopic'' view of cognitive adaptation, encompassing a broad range of fundamental issues from low-level, biological constraints to high-level, symbolic communication.<P><HR><H2>Current Students</H2><ul><LI> <!WA1><A HREF="http://www-cse.ucsd.edu/users/schraudo/"> Nici Schraudolph</A><LI> <!WA2><A HREF="http://www-cse.ucsd.edu/users/tkammeye/"> Tom Kammeyer</A><LI> <!WA3><A HREF="http://www-cse.ucsd.edu/users/mland/"> Mark Land</A><LI> <!WA4><A HREF="http://www-cse.ucsd.edu/users/fil"> Filippo Menczer</A><LI> <!WA5><A HREF="http://www-cse.ucsd.edu/users/crosin/"> Chris Rosin</A><LI> <!WA6><A HREF="http://www-cse.ucsd.edu/users/jhatton/"> John Hatton</A></UL><HR><H2>Distinguished Alumnae</H2><ul><li> Dan Rose <BR> Advanced Technology Group <BR> Apple Computer <BR> rose@apple.com<p><li> John McInerney Advanced Technology Group<BR> Encyclopedia Britannica <BR> john@eb.com<p><LI> <!WA7><A HREF="http://www.cs.sandia.gov/~wehart/main.html"> Bill Hart</A><LI> <!WA8><A HREF="http://www-cse.ucsd.edu/users/steier/"> Amy Steier</A><LI> <!WA9><A HREF="http://www-cse.ucsd.edu/users/wwilluhn/"> Wolfram Willuhn</A></ul><HR><!WA10><A HREF="http://www.cs.wisc.edu/~belew/ccsrg.gif2"> If you want to see a picture... </A></BODY><P><ADDRESS><i>rik@cs.ucsd.edu </i></ADDRESS>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -