Path: utzoo!utgpu!watserv1!watmath!att!rutgers!apple!usc!cs.utexas.edu!tut.cis.ohio-state.edu!dendrite.cis.ohio-state.edu!pollack From: pollack@dendrite.cis.ohio-state.edu (Jordan B Pollack) Newsgroups: comp.ai.philosophy Subject: Re: Reasoning Paradigms Summary: The mouse takes the cheese Message-ID: Date: 18 Oct 90 05:41:10 GMT References: <3586@media-lab.MEDIA.MIT.EDU> <69347@lll-winken.LLNL.GOV> <3593@media-lab.MEDIA.MIT.EDU> <69377@lll-winken.LLNL.GOV> <11@tdatirv.UUCP> <3642@media-lab.MEDIA.MIT.EDU> <22@tdatirv.UUCP> <3680@media-lab.MEDIA.MIT.EDU> Sender: news@tut.cis.ohio-state.edu Reply-To: pollack@cis.ohio-state.edu Organization: Ohio State Computer Science Lines: 90 In-reply-to: minsky@media-lab.MEDIA.MIT.EDU's message of 12 Oct 90 13:12:38 GMT Marvin Minsky has turned up the heat in this newsgroup, with the folksy "lets not choose sides" attack on connectionism he offered in PERCEPTRONS'88. Since a few people have already argued these points (or conceded to his authority!) I will collect most of the arguable material in one place: 1) He (again) chose non-recurrent backprop as a strawman representative of the entire field. He also claimed that 2) nothing useful could come out of the weights of a network, that 3) the field is "muddled" on terminology for "compound" architectures, and that 4) the central goal of the field is to find a homogeneous NN to solve the tabula-rasa-to-genius learning problem. I briefly respond: 1) the strawman can be ignored because he carefully hedged the overgeneralization gambit (this time) with parenthetical references to recurrent networks. 2) several researchers have found classical algorithms (principal components, hierarchal clustering) implemented in the procedures of networks.(e.g. Cottrell, Granger) 3) many researchers work on "architectures" composed of "modules" without getting muddled,(e.g. Jacobs, Ballard) 4) this is equivalent to accusing AI of having the goal of programming just one genius program. But most of this noise is still about the decades-old controversy over the relative promise of the bottom-up and top-down approaches to studying cognition. This promise can be assessed by seeing what sort of corner your theory backs you into: >>Where is the >>"traditional, symbolic, AI in the brain"? The answer seems to have >>escaped almost everyone on both sides of this great and spurious >>controversy! The 'traditional AI' lies in the genetic specifications >>of those functional interconnections: the bus layout of the relations >>between the low-level networks. A large, perhaps messy software is >>there before your eyes, hiding in the gross anatomy. I have to admit this is definitely a novel version of the homunculus fallacy: If we can't find him in the brain, he must be in the DNA! Of all the data and theories on cellular division and specialization and on the wiring of neural pathways I have come across, none have indicated that DNA is using means-ends analysis. Certainly, connectionist models are very easy to decimate when offered up as STRONG models of children learning language, of real brains, of spin glasses, quantum calculators, or whatever. That is why I view them as working systems which just illuminate the representation and search processes (and computational theories) which COULD arise in natural systems. There is plenty of evidence of convergence between representations found in the brain and backprop or similar procedures despite the lack of any strong hardware equivalence (Anderson, Linsker); constrain the mapping task correctly, and local optimization techniques will find quite similar solutions. Furthermore, the representations and processes discovered by connectionist models may have interesting scaling properties and can be given plausible adaptive accounts. On the other hand, I take it as a weakness of a theory of intelligence, mind or language if, when pressed to reveal its origin, shows me a homunculus, unbounded nativism, or some evolutionary accident with the same probability of occurrence as God. (Chomsky's corner). So, the age-old question of conflicting promise can be rephrased as follows, either being a valid philosophical approach to AI: Should we study search and representation as they occur in nature, or as algorithm and data-structure in artificial symbolic systems? I choose the former, since nature seems to have solved many problems which continue to haunt the not-so-young-anymore engineering field of AI. -- Jordan Pollack Assistant Professor CIS Dept/OSU Laboratory for AI Research 2036 Neil Ave Email: pollack@cis.ohio-state.edu Columbus, OH 43210 Fax/Phone: (614) 292-4890