Date: Thu 14 Jan 1988 21:56-PST From: AIList Moderator Kenneth Laws Reply-To: AIList@SRI.COM Us-Mail: SRI Int., 333 Ravenswood Ave., Menlo Park, CA 94025 Phone: (415) 859-6467 Subject: AIList V6 #10 - Intelligence, MLNS Neural Network Tool Set To: AIList@SRI.COM Status: RO AIList Digest Friday, 15 Jan 1988 Volume 6 : Issue 10 Today's Topics: Queries: Table-Tennis-Playing Robot & M. Selfridge & TRC Users & Graphical Representation of Rule Base, Philosophy - Evolution of Intelligence & Empirical Science, Neuronal Systems - MLNS Public-Domain Simulator Tool Set Effort ---------------------------------------------------------------------- Date: 14 Jan 88 00:32:47 GMT From: dlfe91!hucka@umix.cc.umich.edu (Michael Hucka) Subject: query: table-tennis-playing robot? Within the last half-year I read an article which described a successful robotic device capable of playing table-tennis. Unfortunately I can't remember where I came across it. Has anyone else read about this or know where I can get more information about it? I am interested in learning about the research and technical issues the system's creators had to address. Mike -- |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||| Computer Aided Engineering Network, University of Michigan, Ann Arbor MI 48109 ARPA: hucka@caen.engin.umich.edu ------------------------------ Date: 14 Jan 88 20:04:39 GMT From: ece-csc!ncrcae!gollum!rolandi@mcnc.org (rolandi) Subject: M. Selfridge Does anyone know the email (or other mail) address of M. Selfridge of: Selfridge, M. 1980. A Process Model of Language Acquisition. Ph.D. diss., Technical Report, 172, Dept of Computer Science, Yale University. ? Thanks. walter rolandi rolandi@gollum.UUCP () NCR Advanced Systems, Columbia, SC u.s.carolina dept. of psychology and linguistics ------------------------------ Date: 12 Jan 88 02:41:49 GMT From: linc.cis.upenn.edu!levy@super.upenn.edu (Joshua Levy) Subject: Looking for TRC users I'm interested in how many people are using TRC, and what they are using it for. If you use TRC, plan to, or are just interested in it, please send me email. (Especially if you have modified or improved it in any way.) Thanks. TRC: Translate Rules to C, is a program which takes an OPS like rule language and compiles it into C code. It is a PD program. Joshua Levy levy@linc.cis.upenn.edu ------------------------------ Date: 14 Jan 88 12:11:57 GMT From: mcvax!hermanl@uunet.uu.net (Herman Lenferink) Subject: graphical representation of rule base I am searching for algorithms / approaches to represent a (production) rule base in the form of a graph / tree. The premise of a rule can have several conditions, connected with AND / OR connectives. A rule may also have more than one conclusion (using an AND connective). However, I am also interested in suggestions for representations of other rule formats. Any hints, literature references, or even source code are VERY welcome. If there is interest, I will summarize the responces. Thanks in advance, Herman Lenferink CWI, Amsterdam, Netherlands hermanl@piring.cwi.nl ------------------------------ Date: 14 Jan 88 07:30:59 GMT From: well!wcalvin@lll-crg.llnl.gov (William Calvin) Reply-to: well!wcalvin@lll-crg.llnl.gov (William Calvin) Subject: Re: Evolution of Intelligence My favorite short definition is that of Horace B. Barlow in 1983: "Intelligence... is the capacity to guess right by discovering new order." There are some related quotes at p.187 of my book THE RIVER THAT FLOWS UPHILL. William H. Calvin University of Washington NJ-15, Seattle WA 98195 wcalvin@well.uucp 206/328-1192 ------------------------------ Date: Tue, 5 Jan 88 11:50 EST From: Bruce E. Nevin Subject: empirical science of language [Excerpted from the NL-KR Digest. Bruce mentions fundamental difficulties in the study of lingistics and psychology. Are there similar viewpoints on AI? Roger Schank mentions at least one in his recent AI Magazine article: If AI is the study of uniquely human capabilities, then any algorithm derived from AI negates its own domain. -- KIL] The status of linguistics as a science has been a vexed question for a very long time. There are a number of good reasons. Probably the central one is this: in all other sciences and in mathematics, you can rely on the shared understanding of natural language to provide a metalanguage for your specialized notations and argumentation. In linguistics you cannot without begging fundamental questions that define the field. There is an exactly parallel difficulty in psychology: a psychological model must account for the investigator on the same terms as it accounts for the object of investigation. The carefully crafted suspension of subjectivity that is so crucial to experimental method becomes unattainable when subjectivity itself is the subject. (See Winograd's recent work, e.g. _Understanding Computers and Cognition_ for reasons why computer modelling of natural language is not possible, on the usual construal of what computer modelling is. I have references to work that gets around this "Framer Problem" if you are interested.) [...] ------------------------------ Date: Sun, 10 Jan 88 22:05:37 EST From: weidlich@ludwig.scc.com (Bob Weidlich) Subject: MLNS Announcement A PROPOSAL TO THE NEURAL NETWORK RESEARCH COMMUNITY TO BUILD A MULTI-MODELED LAYERED NEURAL NETWORK SIMULATOR TOOL SET (MLNS) Robert Weidlich Contel Federal Systems January 11, 1988 The technology of neural networks is in its infancy. Like all other major new technologies at that stage, the development of neural networks is slowed by many impediments along the road to realizing its potential to solve many sig- nificant real world problems. A common assumption of those on the periphery of neural network research is that the major factor holding back progress is the lack of hardware architectures designed specifically to implement neural networks. But those of us who use neural networks on a day to day basis real- ize that a much more immediate problem is the lack of sufficiently powerful neural network models. The pace of progress in the technology will be deter- mined by the evolution of existing models such as Back Propagation, Hopfield, and ART, as well as the development of completely new models. But there is yet another significant problem that inhibits the evolution of those models: lack of powerful-yet-easy-to-use, standardized, reasonably- priced toolsets. We spend months of time building our own computer simula- tors, or we spend a lot of money on the meager offerings of the marketplace; in either case we find we spend more time building implementations of the models than applying those models to our applications. And those who lack sophisticated computer programming skills are cut out altogether. I propose to the neural network research community that we initiate an endeavor to build a suite of neural network simulation tools for the public domain. The team will hopefully be composed of a cross-section of industry, academic institutions, and government, and will use computer networks, pri- marily Arpanet, as its communications medium. The tool set, hereinafter referred to as the MLNS, will ultimately implement all of the significant neural network models, and run on a broad range of computers. These are the basic goals of this endeavor. 1. Facilitate the growth and evolution of neural network technology by building a set of powerful yet simple to use neural network simula- tion tools for the research community. 2. Promote standardization in neural network tools. 3. Open up neural network technology to those with limited computer expertise by providing powerful tools with sophisticated graphical user interfaces. Open up neural network technology to those with limited budgets. 4. Since we expect neural network models to evolve rapidly, update the tools to keep up with that evolution. This announcement is a condensation of a couple of papers I have written describing this proposed effort. I describe how to get copies of those docu- ments and get involved in the project, at the end of this announcement. The MLNS tool will be distinctive in that will incorporate a layered approach to its architecture, thus allowing several levels of abstraction. In a sense, it is a really a suite of neural net tools, one operating atop the other, rather than a single tool. The upper layers enable users to build sophisti- cated applications of neural networks which provide simple user interfaces, and hide much of the complexity of the tool from the user. This tool will implement as many significant neural network models (i.e., Back Propagation, Hopfield, ART, etc.) as is feasible to build. The first release will probably cover only 3 or 4 of the more popular models. We will take an iterative approach to building the tool and we will make extensive use of rapid prototyping. I am asking for volunteers to help build the tool. We will rely on computer networks, primarily Arpanet and those networks with gateways on Arpanet, to provide our communications utility. We will need a variety of skills - pro- grammers (much of it will be written in C), neural network "experts", and reviewers. Please do not be reluctant to help out just because you feel you're not quite experienced enough; my major motivation for initiating this project is to round-out my own neural networking experience. We also need potential users who feel they have a pretty good feel for what is necessary and desirable in a good neural network tool set. The tool set will be 100% public domain; it will not be the property of, or copyrighted by my company (Contel Federal Systems) or any other organization, except for a possible future non-commercial organization that we may want to set up to support the tool set. If you are interested in getting involved as a designer, an advisor, a poten- tial user, or if you're just curious about what's going on, the next step is to download the files in which I describe this project in detail. You can do this by ftp file transfer and an anonymous user. To do that, take the follow- ing steps: 1. Set up an ftp session with my host: "ftp ludwig.scc.com" (Note: this is an arpanet address. If you are on a network other than arpanet with a gateway to arpanet, you may need a modified address specification. Consult your local comm network guru if you need help.) [Note: FTP generally does not work across gateways. -- KIL] 2. Login with the user name "anonymous" 3. Use the password "guest" 4. Download the pertinent files: "get READ.ME" (the current status of the files) "get mlns_spec.doc (the specification for the MLNS) "get mlns_prop.doc (the long version of the proposal) If for any reason you cannot download the files, then call or write me the following address: Robert Weidlich Mail Stop P/530 Contel Federal Systems 12015 Lee Jackson Highway Fairfax, Virginia 22033 (703) 359-7585 (or) (703) 359-7847 (leave a message if I am not available) ARPA: weidlich@ludwig.scc.com ------------------------------ End of AIList Digest ********************