miller@CS.ROCHESTER.EDU (Brad Miller) (03/07/90)
OK, lots of recent bashing of "knowledge engineering" but I'd like to clarify a few things.... while "ke" is overused and misused, and I'm not sure what the hell it means anymore one shouldn't necessarily retreat to behavioristic approaches (that is, an approach that models intelligent behavior as has been recently suggested here). What it does mean, is that once cannot do ke for music because there aren't any decent KRs yet (knowledge representations). I think developing a good kr for musical "rules", both in terms of basic music theory (e.g. what scales seem to sound good, or why modulating the tonic to the fourth and fifth is a good progression..) and for certain stylistic information is necessary before any real work can proceed anywhere. In some sense this is an argument against neural net approaches, etc. because while one may be able to come up with a system which happens to behave nicely, one cannot in any sense describe what the system actually "know"s. KE, for music, then, consists of taking this kr, from which one can theoretically come up with music charts, and actually encode the special (stylistic/performance) and general (theoretic) knowledge. The goal would not be, of course, to simply have a prolog-like program that could generate a valid musical piece, but rather to have a prolog-like program that could act as an intelligent arranger/compositional enhancement tool. (not that the UI would in any sense be prolog-like of course, I would simply hope to encode the knowledge in this fashon). Something of an expert system in the general sense, although the techniques would actually come more from the planning and natural language domains (since a peice of music is very much like a plan to be executed: one wants to acheive certain goals, they must be done in some temporal order, and things like duration are crucial to acheiving particular effects. My work is much too sketchy at this point to present anything too cogent here (e.g. the rule structures), but the point is, as someone in the AI research field, I don't think one should discard non-behavioristic approaches too quickly. They have the theoretical advantages of being able to build a system that can be well understood, both in terms of construction, programming, and interpreting of results. Connectionist approaches may well make a better music composer in the long term, but until problems like "appropriate motivation" for these systems are solved, I'm not convinced we will personally appreciate the output. (i.e. why do you think a system that doesn't enjoy music would write good symphonies?) Provocatively yours,
mgresham@artsnet.UUCP (Mark Gresham) (03/15/90)
In article <12275@venera.isi.edu> smoliar@vaxa.isi.edu.UUCP (Stephen Smoliar) writes: >This hypothesis is appealing because it implies that we may "engineer" >knowledge, just as we "engineer" circuits. It's simply a matter of developing >our understanding of how to put things together. However, IT IS STILL ONLY A >HYPOTHESIS. Certainly, the track record of expert systems offers no sound >confirmation of that hypothesis. Indeed, the ways in which the behavior of >expert systems deviates from that of humans may ultimately detract from the >hypothesis. Nevertheless, we are going to be very reluctant to give that >hypothesis up because we have a long intellectual tradition which allows >us to reason about ASSEMBLING THINGS and inclines us to raise eyebrows at >any mention of epiphenomena. > >Connectionism is definitely a step away from the knowledge level hypothesis, >for precisely the reason Brad pointed out: you cannot talk about the knowledge >contained in a neural net the way you can talk about the contents of a >knowledge base. At the same time, Brad is also right in wanting to have >a way to interact with any system about "what it knows." However, I don't >think any of us would like a dump of a knowledge base in our attempt to find >out what even a simple expert system "knows." In other words, we are going >down a slippery slope of issues of "knowing about knowledge." Yes, Virginia, >we are talking about CONSCIOUSNESS now. I wonder, Steve, if the difference between what an expert system "knows" and its "knowledge base" is a parallel to the difference between "music" and a "theory of music" -- this all being and intuitive observation on my part. More intuition: what a system (or a person) comes to "know" can alter its "knowledge base" in the same way that one's cumulative experience of "music" can alter one's "theory of music." Cheers, --Mark ======================================== Mark Gresham ARTSNET Norcross, GA, USA E-mail: ...gatech!artsnet!mgresham or: artsnet!mgresham@gatech.edu ========================================