Xref: utzoo comp.ai.neural-nets:1104 comp.ai:5044 Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!aramis.rutgers.edu!tgd From: tgd@aramis.rutgers.edu (Tom Dietterich) Newsgroups: comp.ai.neural-nets,comp.ai Subject: Re: NETtalk results Summary: rule learning algorithms vs backpropagation Message-ID: Date: 12 Nov 89 22:33:10 GMT References: <1690@cod.NOSC.MIL> <77404@linus.UUCP> <13659@orstcs.CS.ORST.EDU> Distribution: usa Organization: Rutgers Univ., New Brunswick, N.J. Lines: 29 In article , nf0a+@andrew.cmu.edu (Nathan W. Fullerton) writes: > > In response to the many messages that have been claiming conventional > rule based methods get more accurate results than NETtalk, I would like > to point out that a accuracy is not the only advantage NETtalk claims. > [...] I've written back > propagation programs in less than 45 pages of LISP code (I've heard > higher numbers are the norm but the programs worked, 87% accuracy on OCR > applications). > We can't take only accuracy into account. Back propagation has other > advantages, small size program code, speed of training, and versatility. > > -Nathan Fullerton ID3 can be implemented in a handfull of functions (4000 bytes). It is a simpler and more direct algorithm that backpropagation. Several studies have shown speed of training for ID3 between 10 and 100 times faster than backpropagation. While ID3 is very versatile, backpropagation *is* definitely more versatile. Rule-based systems (such as those described by Klatt) may attain superior performance. The challenge is to come up with learning methods that can match the performance of hand-crafted rule bases. It looks like neither ID3 nor backpropagation can meet this challenge, but the precise comparative studies have not been done. --Tom Dietterich tgd@cs.orst.edu