Xref: utzoo comp.ai.neural-nets:1098 comp.ai:5043 Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!tut.cis.ohio-state.edu!pt.cs.cmu.edu!andrew.cmu.edu!nf0a+ From: nf0a+@andrew.cmu.edu (Nathan W. Fullerton) Newsgroups: comp.ai.neural-nets,comp.ai Subject: Re: NETtalk results Message-ID: Date: 12 Nov 89 04:10:43 GMT References: <1690@cod.NOSC.MIL> <77404@linus.UUCP> <13659@orstcs.CS.ORST.EDU> <20676@mimsy.umd.edu>, <6936@pt.cs.cmu.edu> Distribution: usa Organization: Carnegie Mellon, Pittsburgh, PA Lines: 17 In-Reply-To: <6936@pt.cs.cmu.edu> 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 am not familiar with the specifics on NETtalk, but I have done some work with back propagation and found that the code is remarkably simple and easy to manipulate, I assume that since NETtalk uses back propagation it also has those same advatages. I've heard that rule based systems can become EXTREMELY large when the application is not strictly conducive to a rule based system. 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