Date: Mon 29 Aug 1988 23:09-EDT From: AIList Moderator Nick Papadakis Reply-To: AIList@mc.lcs.mit.edu Us-Mail: MIT LCS, 545 Tech Square, Rm# NE43-504, Cambridge MA 02139 Phone: (617) 253-6524 Subject: AIList Digest V8 #71 To: AIList@mc.lcs.mit.edu Status: R AIList Digest Tuesday, 30 Aug 1988 Volume 8 : Issue 71 Query: Modelling of spatial knowledge, Dr. Benjamin Kuipers Responses: Category Theory in AI How do I learn about AI, Prolog, and/or Lisp? Speech recognition with neural nets Expert Systems for Statistical Analysis ---------------------------------------------------------------------- Date: Sun, 28 Aug 88 12:56 EDT From: WHANG@HULAW1.HARVARD.EDU Subject: Request on the modelling of spatial knowledge! Hi, there! Does anybody know the computer mail address of Dr. Benjamin Kuipers? He was a profesor in the Department of Mathematics at Tufts University But I am not sure he is still there. I'd like to get some information about his research on the "modelling of spatial knowledge". Does anybody know about the "TOUR model" of the cognitive spatial description? Of if you have some information in this line of research; the "reapresentation and modelling of spatial knowledge", please, let me know! whang at husc3 ( whang@husc3 ) BITNET whang@husc3.harvard.edu (ARPANET) Sang-Min Whang Department of Psychology 33 Kirkland St, Harvard University Cambridge, MA 02138 Thank you for your attention! Sang-Min. ------------------------------ Date: 22 Aug 88 15:35:13 GMT From: linus!philabs!hen3ry!dpb@husc6.harvard.edu (Paul Benjamin) Subject: Re: Category Theory in AI In a previous article, Jack Campin writes: >I can't imagine what category theory has to contribute to knowledge >representation (though I can just about imagine it helping to describe >neural nets in a more abstract way). Can the philabs people say more >about what they're up to? Well, not really, in a public forum. But Mike Lowry of the Kestrel Institute has pointed out that a representation can be viewed as a category, and a shift of representation as a morphism. The question of whether this insight is very productive is open, but at least it gives us a formal notion of representation, and we've built on this some formal notions of abstraction and learning. We'll let you know if this turns out to be fruitful. Paul Benjamin ------------------------------ Date: 22 Aug 88 21:03:24 GMT From: sco!johnwe@uunet.uu.net (John Weber, Celtic sysmom) Subject: Re: How do I learn about AI, Prolog, and/or Lisp In article <398@mfgfoc.UUCP> mike@mfgfoc.UUCP (Mike Thompson) writes: <...> >I have three question which I hope one of you can answer: > >1. I have an IBM/XT at home with the newest version of TURBO PROLOG. >Can I use this system to gain an understanding of AI applications >such as expert systems? If so, what books can help me? I have not >seen Turbo Prolog mentioned in this newsgroup and I fear that >it is considered by experts to be a toy Prolog or an implementation >so neutered as to be worthless. (Creak... Damn, this asbestos suit is getting stiff... ZIP! Humm... Enough nitrogen. Hisssss... POP! Foosh...) My exerence with Turbo "Prolog" was extermely negative. It may be a useful language, but I kinda doubt it. It doesn't support such things as asserting predicates into the data base, the syntax isn't C&M, and it is strongly typed. It is also extremely slow. (Click.) If you can get a hold of C-Prolog or SB-prolog, they are quite acceptable and useful implementations. These are for UN*X. Arity Prolog is a good commercial prolog for the IBM PCish boxes. >2. Does anyone know of classes offered in my area (I live in Los Altos, >California) at local colleges which would teach me Prolog? I have already >checked local community colleges, but their classes are only on >languages such as Fortran, Cobal, Pascal or 'C'. Would I be better taking >a more general class on AI instead of a specific language? Should I >consider Lisp over Prolog? (It came with GNU Emacs and is available on >my Unix system at work.) Lisp and Prolog address different language issues, and are both good and useful languages. Prolog is quite different from most "normal" languages, and may pose certain learning difficulties. My personal favorite Lisps are Kyoto Common Lisp and MIT C-Scheme. They are for UN*X, again. There is a Scheme dialect for Macs, but I've never played with it. Microsoft has a Lisp for MS-DOS (supposedly it is Common Lisp, but again, I haven't played with it). Emacs Lisp is useful in the context of Emacs, but I don't think it would make a good way to learn lisp. I personally like Lisp more than I like Prolog, but that is a taste thing. Lisp can also be much faster. Oh, are you on a 4.* BSD box? If so, there may be Franz Lisp floating around your bin directories. Sun also has a really good Lisp package (or so I'm told). I thought De Anza Jr. College offered an AI class which taught Lisp, but it's been a while since I took a class there. >3. What is the best way to get introduced to the AI field? I'm I >taking the right approach? Any comments would be appreciated. > >Thanks in advance. > No sweat. >Mike Thompson > >--------------------------------------------------------------------------- >Michael P. Thompson FOCUS Semiconductor Systems, Inc. >net: (sun!daver!mfgfoc!engfoc!mike) 570 Maude Court >att: (408) 738-0600 Sunnyvale, CA 94086 USA Please note: these are my own opinions, and in no way reflect the opinions of my employers. -- ############################################################################# # # # # "In the fields of Hell, # John Weber, ...!uunet!sco!johnwe # # where the grass grows high, # @ucscc.ucsc.EDU:johnwe@sco.COM # # are the graves of dreams, # # # allowed to die." -- Author unknown # Celtic sysmom with an ATTITUDE! # # # Any opinions expressed are my own # ############################################################################# ------------------------------ Date: Tue, 23 Aug 88 16:32:36 -0200 From: Antti Ylikoski Subject: Speech recognition with neural nets In AIList Digest V8 #63, att!chinet!mcdchg!clyde!watmath!watvlsi!watale!dixit@bloom-beacon.mit.edu (Nibha Dixit) writes: >Subject: Speech rec. using neural nets >Is anyody out there looking at speech recognition using neural >networks? There has been some amount of work done in pattern >recognition for images, but is there anything specific being done >about speech? In the Helsinki University of Technology, in the Department of Technical Physics, the group of Professor Teuvo Kohonen has been studying the usage of neural nets for speech recognition for several years. Professor Kohonen gave a talk on their results in the Finnish AI symposium in this year. They have an experimental system which uses a neural net board in a PC. I cannot remember whether the paper is written in English or in Finnish, but should you wish to get the symposium proceedings, contact Finnish Artificial Intelligence Society (FAIS) c/o Dr Antti Hautamaeki HM & V Research Helsinki, Finland I understand Kohonen's results are comparable to other approaches to speech recognition. --- Andy ------------------------------ Date: Sun, 28 Aug 1988 21:05-EDT From: Kai-Fu.Lee@SPEECH2.CS.CMU.EDU Subject: Speech rec. using neural nets In response to Nibha Dixit's question about speech recognition using neural networks, I would recommend the following two articles by Richard Lippmann: An Introduction to Computing with Neural Nets, IEEE ASSP Magazine, Vol. 4, No. 2, April 1987. Neural Nets for Computing, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April, 1988. The ICASSP conference proceedings contain quite a few interesting papers on speech recognition with neural networks. Kai-Fu Lee Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213 ------------------------------ Date: Mon, 29 Aug 88 11:19:19 EST From: cik@l.cc.purdue.edu (Herman Rubin) Subject: Re: Expert Systems for Statistical Analysis In a previous article, KDM2520@TAMSIGMA.BITNET writes: > If anyone on the list is aware of any commercial expert systems which do > statistical analysis, I sure would appreciate the information. I am looking > for expert statistical analysis packages which process data, analyze > correlation etc., forecast trends, detect regeneration cycles, and so on. > I have looked through AI Magazine, IEEE Expert and several Computer journals > and I couldn't see any such product advertisements. Could someone who is > aware of such expert statistical analysis packages send me the info please? > > Thank you. MURALI@TAMLSR (bitnet) There are things that a computer is capable of doing, but this is not one of them. Statistics is not a black box into which one can put data and come out with the state of the universe. To analyze a problem, it is necessary for the user to input a model, or better, a collection of models. The user must realize that many assumptions must be made. It is advisable to have a good mathematical statistician available to point out the consequences of the model which the user does not realize have been inserted. Analyze correlation indeed! It is extremely rare that correlation has anything to do with the real problem. In addition, the user must have an evaluation of the consequences of an incorrect action. Massive statistical uncertainty may be irrelevant if the resulting action is unaffected, and small uncertainty may be very important if the effects of a wrong action are sufficiently great. I personally have worked on this problem, and the difficulties are major. Statistical packages of the type to use this input, when well formulated, are still in the development stage. -- Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907 Phone: (317)494-6054 hrubin@l.cc.purdue.edu (Internet, bitnet, UUCP) ------------------------------ End of AIList Digest ********************