Xref: utzoo comp.ai:5048 comp.ai.neural-nets:1106
Path: utzoo!censor!geac!jtsv16!uunet!wuarchive!brutus.cs.uiuc.edu!uakari.primate.wisc.edu!dogie.macc.wisc.edu!uwvax!umn-d-ub!umn-cs!hougen
From: hougen@umn-cs.CS.UMN.EDU (Dean Hougen)
Newsgroups: comp.ai,comp.ai.neural-nets
Subject: Re: Backpropagation applications
Summary: Sentences
Keywords: Neural Networks, Efficient Learning
Message-ID: <16883@umn-cs.CS.UMN.EDU>
Date: 10 Nov 89 01:20:24 GMT
References: <1690@cod.NOSC.MIL> <77404@linus.UUCP> <13659@orstcs.CS.ORST.EDU>
Reply-To: hougen@umn-cs.cs.umn.edu (Dean Hougen)
Organization: CSci Dept., University of Minnesota, Mpls.
Lines: 24

In article <13659@orstcs.CS.ORST.EDU> tgd@orstcs.CS.ORST.EDU (Tom Dietterich) writes:
>Your accuracy claims for NETtalk are greatly exaggerated.  I have
>replicated the NETtalk study using the same training data.  In this
>case, training on 1000 words chosen at random from the 20000-word
>dictionary provided by Sejnowski.
                                        ^^^^^^
>Testing is performed on a randomly chosen test set of 1000 words.
                           ^^^^^^^^

I was under the impression that Sejnowski had NETtalk read real sentences in
real paragraphs, not randomly ordered words.  Right?

BTW, did you present the input as one long string of charcters with the words
seperated by a single space or did you present the words one at a time (i.e.
as a long string of characters with the words seperated by three or more 
spaces) or did you do something else (what?)?

I'll leave you to determine what effect any of this could have on NETtalk's
performance.

Dean Hougen
--
"Stop making sense.  Stop making sense.  Stop making sense, making sense."
    - Talking Heads, "Stop Making Sense," _Stop Making Sense_