home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Monster Media 1993 #2
/
Image.iso
/
text
/
9305nni.zip
/
930513.BIB
/
comp.ai.neural-nets_9002_000000.msg
next >
Wrap
Text File
|
1993-05-13
|
2KB
|
45 lines
Newsgroups: comp.ai.neural-nets
Path: serval!netnews.nwnet.net!usenet.coe.montana.edu!saimiri.primate.wisc.edu!sdd.hp.com!swrinde!news.dell.com!natinst.com!cs.utexas.edu!zaphod.mps.ohio-state.edu!menudo.uh.edu!nuchat!texhrc!texhrc!pyeatt
From: pyeatt@Texaco.com (Larry D. Pyeatt)
Subject: Re: neurode "fatigue" and sequential outputs.
Message-ID: <1993May6.151258.3914@texhrc.uucp>
Sender: news@texhrc.uucp
Nntp-Posting-Host: 211.2.1.65
Organization: Texaco
References: <1993May4.154939.13152@sinkhole.unf.edu>
Date: Thu, 6 May 1993 15:12:58 GMT
Lines: 32
In article <1993May4.154939.13152@sinkhole.unf.edu>, sharsh@magic.cis.unf.edu (Samuel Harshbarger) writes:
|>
|> I'd like to have a network that, when given an input pattern,
|> produces a sequence of output patterns. It seems that this could be
|> done by changing the activation function and the timing relationship of
|> input to output.
You may want to look at the Avalanche neural network.
@article{grossberg1,
author = "Stephen Grossberg",
title = "Some Networks that can Learn, Remember, and Reproduce any Number of Complicated Space-Time Patterns {I}",
journal = "Stuc. Appl. Math",
volume = "49",
pages = "pp. 53---91",
year = "1970"}
@article{grossberg2,
author = "Stephen Grossberg",
title = "Some Networks that can Learn, Remember, and Reproduce any Number of Complicated Space-Time Patterns {II}",
journal = "Stuc. Appl. Math",
volume = "49",
pages = "pp. 135---166",
year = "1970"}
--
Larry D. Pyeatt The views expressed here are not
Internet : pyeatt@texaco.com those of my employer or of anyone
Voice : (713) 975-4056 that I know of with the possible
exception of myself.