Copy Link
Add to Bookmark
Report
Neuron Digest Volume 03 Number 10
NEURON Digest Tue Apr 12 10:03:41 CDT 1988 Volume 3 / Issue 10
Today's Topics:
Re: request for net software
Hopfield Neural Network Simulator
FREE!!! NEURAL NETWORK SOFTWARE FOR DOWNLOADING!!!
ICNN vs INNS
TODAY: Adaptive Networks Colloquium -- Dan Hammerstrom
Confreence Announcement
Neural Network research in Japan. Conference program
----------------------------------------------------------------------
Date: 7 Apr 88 06:10:28 GMT
From: Galo Mejia <spl1!laidbak!mejia@elroy.jpl.nasa.gov>
Subject: Re: request for net software
Does anyone knows if programs like the game of life (posed by J. Conway)
has been implemented in the Connection machine, to study image-processing ?.
Any ideas about the subject ? maybe I'am totally out of focus.
Thanks in advance, Galo.
------------------------------
Date: Mon, 11 Apr 88 11:23:03 CDT
From: R_OSHEA@OTAGO.AC.NZ.CSNET
Subject: For Neural Net BB
Is anyone using connectionist ideas to model stereoptic depth perception,
and binocular fusion, or has the field been cornered
by Marr, Poggio, Grimson, Frisby, et al?
Robert P. O'Shea,
Department of Psychology,
University of Otago,
P.O. Box 56,
Dunedin,
New Zealand.
R_OSHEA%OTAGO.AC.NZ%waikato.ac.nz@RELAY.CS.NET
------------------------------
Date: 29 Mar 88 16:15:16 GMT
From: Ken Burgess RCD <pioneer!burgess@AMES.ARC.NASA.GOV>
Subject: Re: request for net software
In article <346@c10sd1.StPaul.NCR.COM> johnson@ncrcce.StPaul.NCR.COM (Wayne D. T. Johnson) writes:
>I have recently read an article on neural nets in the last issue of discovery
>(I think). As a software Engineer (AKA Programmer) I would be very
>interested if any one out there could direct me to a source of Public
>Domain (term used genericly, including such classes as shareware,
>freeware, etc.) software for UNIX or an IBM PC/Compatible that could be
>useful to a basement experimentor such as I.
>
>I would also like to start a list of basic texts containing information
>on nets. Not that some of the information in this group isn't useful
>its just that sometimes it goes so far over my head....
>
>If any one would like to contribute any information, please send it to me via
>E-mail.
>
>If any one would like a copy of what I receive, send me a self addressed
>stamped E-mail envlope and I will try to send it back.
>
Since I suspect that there are many new and introductory readers on this
newsgroup, and the traffic is not all that heavy, I feel that it would
be very helpful to post whatever information is available for computer
systems, software, resources, texts, etc.
Ken Burgess UUCP: {topaz,lll-crg,ucbvax}!
Mail Stop: 233-9 ames!pioneer!burgess
NASA-Ames Research Center ARPA: burgess%pioneer@ames.arc.nasa.gov
Moffett Field, CA 94035 ARPA: burgess@pioneer.arc.nasa.gov
(415)-694-6347 ARPA: burgess@ames-pioneer.arpa
------------------------------
Date: 2 Apr 88 01:30:34 GMT
From: Grobbins <sdcc6!sdcc8!cs178aas@ucsd.edu>
Subject: Re: request for net software
In article <1627@netmbx.UUCP> muhrth@db0tui11.BITNET (Thomas Muhr) writes:
>>
I've written a backprop in generic Pascal with nothing extraneous
(except momentum) thrown in. It's not particularly efficient, but
was designed just to straightforwardly implement a basic backprop
algorithm. If there's interest, I can clean up the source and make
it available. Send mail if you'd like a copy.
Grobbins grobbins@ucsd.edu
.uucp
.BITNET
God didn't create the world in seven days.
He rested for six and then pulled an all-nighter. - Diana Jacokes
------------------------------
Date: 6 Apr 88 03:13:44 GMT
From: John K Sun <ucsdhub!hp-sdd!ncr-sd!ncrcae!hubcap!johnsun@sdcsvax.ucsd.edu>
Subject: Hopfield Neural Network Simulator
hello folks,
My recent Hopfield Neural Network should only be used for educational
purposes ONLY. Please contact me *FIRST* for improvements, changes,
bug reports, comments, etc.
johnsun@hubcap.clemson.edu
------------------------------
Date: 31 Mar 88 23:55:52 GMT
From: "Thomas M." <mcvax!unido!tub!tmpmbx!netmbx!morus@uunet.uu.net>
Subject: Re: request for net software
In article <6628@ames.arpa> burgess@pioneer.UUCP (Ken Burgess RCD) writes:
>>
You are absolutely right!
Some time ago there was a little bit more traffic in this newsgroup and
a neural network program named bpsim was posted by Richard Caasi (Oct. 87)
which was written in C and demonstrated a small example of the back-propa-
gation algorithm. This program and the idea behind it is explained in an
article by William P. Jones and Josiah Hoskins "Back-Propagation" in BYTE
Vol. 12, No. 11 August 1987 p. 155-162. J. Hoskins is also the author of the
program.
I did draw a copy of this program - but I weren't very lucky in compiling it
using Turbo-C. It worked once and a while, though I'm not sure that it wasn't
subtly spoiled in the transfer. I am no "C-Crack" and didn't want to bother
people who are.
Maybe some of the above mentioned "listens" and repost the program (wasn't so
big, about 16KB) together with some instruction to activate under Turbo-C. I
have the source available, but I don't know if I have the right to post it.
There is another introductory article and a program listing in C in Dr.Dobb's
Journal #126 April 1987 by Robert Jay Brown "An Artificial Neural Network
Experiment". The program simulates an "adaptive template matching image
categorizer". It "learns to recognize (visual) patterns by being trained
from a set of prototype patterns presented in a training file".
I didn't have the time to "hack" it into my PC, maybe someone else has and
kindly post it to this newsgroup?
Hope this is some new information to you.
-- Thomas
------------------------------
Date: 6 Apr 88 18:13:52 GMT
From: "David M. Neves" <ai!neves@speedy.cs.wisc.edu>
Subject: Re: request for net software
In article <Mar.28.19.05.11.1988.4220@vanhalen.rutgers.edu> pratt@vanhalen.rutgers.edu (Lorien Y. Pratt) writes:
>I just received "Explorations in Parallel Distributed Processing"
>(PDP volume 3) in the mail. This has lots of interesting simulation
>software in it.
>
>Would someone care to send me a unix-uploaded version so that I don't
>have to do it myself?
>--
You can find the software as
pdp2 or pdp1.Z (the compressed version) at
loon.cs.wisc.edu (128.105.2.137)
After uncompressing the file run tar on it
i.e. uncompress pdp1
tar -xf pdp1
grab the file with ftp
i.e.
ftp loon.cs.wisc.edu (or ftp 128.105.2.137)
(user ftp, password anything -- note that anonymous login doesn't work)
binary (go into binary)
get pdp1.Z
quit
The software will not do you any good without the book so get the book
first.
David Neves, Computer Sciences Department, University of Wisconsin-Madison
Usenet: {rutgers,ucbvax,ihnp4}!uwvax!neves
Arpanet: neves@cs.wisc.edu
------------------------------
Date: 1 Apr 88 19:32:00 GMT
From: Doug Salot <amdahl!oliveb!felix!dhw68k!feedme!doug@ames.arc.nasa.gov>
Subject: Re: request for net software
> Wayne D. T. Johnson writes:
> I would be very
>interested if any one out there could direct me to a source of Public
>Domain ... software for UNIX or an IBM PC/Compatible that could be
>useful to a basement experimentor such as I.
While not free, the PDP group's long awaited "volume 3," _Explorations
in Parallel Distributed Processing: A Handbook of Models, Programs, and
Excercises_ is now shipping from The MIT Press, Cambridge, MA, $27.50.
Contents include tunable programs, source code, and excercises for
interactive activation and competetion, constraint satisfaction,
pattern associators, the generalized delta rule, auto-associators
and competetive learning, and cognition modeling.
- Doug
--
Doug Salot || doug@feedme.UUCP || {trwrb,hplabs}!felix!dhw68k!feedme!doug
------------------------------
Date: 4 Apr 88 23:01:27 GMT
From: Richard Caasi <ucsdhub!jack!sdsu!caasi@sdcsvax.ucsd.edu>
Subject: FREE!!! NEURAL NETWORK SOFTWARE FOR DOWNLOADING!!!
The requested neural network programs have been posted to
comp.binaries.ibm.pc in 5 parts.
------------------------------
Date: 7 Apr 88 06:48:32 GMT
From: "Donald C. Brady" <mnetor!utgpu!brady@uunet.uu.net>
Subject: Re: request for net software
I found that the reason that BPSIM does not work is that it fails to
initialize the storage obtained in the create_unit function. It can
be corrected by adding the lines:
unitptr->inlinks = NULL;
unitptr->outlinks = NULL;
just before the return statement in the definition of create_unit.
With this change, it works fine under Borland Turbo C (and also
Microsoft C, I believe).
------------------------------
Date: 29 Mar 88 00:05:15 GMT
From: "Lorien Y. Pratt" <paul.rutgers.edu!vanhalen.rutgers.edu!pratt@rutgers.edu>
Subject: Re: request for net software
I just received "Explorations in Parallel Distributed Processing"
(PDP volume 3) in the mail. This has lots of interesting simulation
software in it.
Would someone care to send me a unix-uploaded version so that I don't
have to do it myself?
=====
Lorien Y. Pratt Computer Science Department
pratt@paul.rutgers.edu Rutgers University
Busch Campus
(201) 932-4714 Piscataway, NJ 08854
------------------------------
Date: Mon, 11 Apr 88 13:30:57 CDT
From: gately@resbld.csc.ti.com (Michael T. Gately)
Subject: ICNN vs INNS
It seems that there is (and will probably continue to be) some
confusion about two of the many conferences on neural networks.
I was asked to make this short message to try to get things
straight.
IEEE Annual International Conference on Neural Networks (IEEE ICNN)
July 24-27, 1988
Sheraton Harbor Island East Hotel (619) 692-2265
San Diego, California
Deadline for full Papers: April 13, 1988 (extended)
Until June 30: $240 After June 30: $280
For more information: Nomi Feldman (619) 453-6222
Annual Meeting of the International Neural Network Society (INNS)
September 6-10, 1988
Boston Park Plaza Hotel (800) 225-2008
Boston, Masachusetts
Deadline for Abstracts: March 31, 1988
INNS Member: $175 Non-member: $220
For more information: (619) 451-3752
------------------------------
Date: Tue, 29 Mar 88 08:49:36 PST
From: Mark Gluck <netlist@PSYCH.STANFORD.EDU>
Subject: TODAY: Adaptive Networks Colloquium -- Dan Hammerstrom
Stanford University Interdisciplinary Colloquium Series:
Adaptive Networks and their Applications
March 29th (Tuesday, 3:15pm)
"Casting Neural Networks into Silicon:
there's good news, and there's bad news"
DAN HAMMERSTROM
Computer Science&Engineering
The Oregon Graduate Center
Abstract
--------
Researchers are developing neural-like network models that exhi-
bit a broad range of cognitive behavior. Unfortunately, existing
computer systems are limited in their ability to emulate such
networks efficiently. Consequently, the OGC Cognitive Architec-
ture Project is studying the implementation of massively parallel
architectures for the emulation of a range of very large
connectionist/neural networks. The goal of our project is to
build ultra-large-scale-integrated, silicon-based computing
structures that will be able to emulate connectionist/neural net-
works with thousands of nodes and millions of connections at
rates exceeding that of their biological counterparts. The
manufacturing costs for these systems will be a few thousand dol-
lars. Such ultra-large die size (larger than the traditional 1
square centimeter) is made possible by the inherent fault-
tolerance of the computational model. This talk will explore
some of the problems and potential solutions in developing such
architectures.
. . . .
Format: Tea will be served 15 minutes prior to the talk, outside
the lecture hall. The talks (including discussion) last about
one hour. Following the talk, there will be a reception in
the fourth floor lounge of the Psychology Dept.
Location: Room 380-380W, which can be reached through the lower level
between the Psychology and Mathematical Sciences buildings.
Technical Level: These talks will be technically oriented and are intended
for persons actively working in related areas. They are not intended
for the newcomer seeking general introductory material.
Information: For additional information, contact Mark Gluck
(gluck@psych.stanford.edu) 415-725-2434.
* * *
Co-Sponsored by: Departments of Electrical Engineering (B. Widrow) and
Psychology (D. Rumelhart, M. Gluck), Stanford Univ.
------------------------------
Date: Thu, 31 Mar 88 17:27:10 CST
From: "Stan C. Kwasny" <wuibc!wucs1!wucs2!sck@mcnc.org>
Subject: Conference Announcement
Announcement
Ninth European Meeting on Cybernetics and Systems Research
Symposium K:
Parallel Distributed Processing in Man and Machine
Chairs: David E.Rumelhart (Stanford)
Georg Dorffner (Vienna)
April 5-8, 1988
University of Vienna, Austria
The following papers will be presented:
Interspike Interval Histograms in a Simple Network Consisting of
Universal Pattern Generators
T.Toth, E.Labos, Hungary.
Neuronal Operations on Asynchronous Time Scale Emulated with
Synchronous Models
E.Labos,Hungary
Short-Term Memory as a Metastable State; A Model of Neural
Oscillator for a Unified Submodule.
A.B.Kirillov et.al., USSR.
Short-Term Memory as a Metastable State; "Neurolocator", a
Model of Attention.
V.I.Kryukov, USSR.
Neural Computation Research for Vision - Simulation on a
Parallel Processing Computer
S.Miyake, T.Inui, Japan.
Crossbar Adaptive Array: A PDP Learning Problem Solver.
S.Bozinovski, Yugoslavia.
INVITED LECTURE: Analyzing Sub-Symbolic Computation and
Representation
P.Smolensky, Colorado, USA.
Infinite Behavior in Connectionist Models with Asymmetric
Weights.
S.Porat, Rochester, USA.
A PDP System for Goal-Plan Decisions
N.E.Sharkey, England.
Modelling Gestalt-Phenomena in a Distributed 'Rule'-System.
G.Dorffner, Austria.
Can Parallel Distributed Processing Provide Anything New?
G.Schwarz, Colorado, USA.
On opening day (April 5), Prof.Rumelhart will give a plenary
lecture on 'Brain Style Computation'.
Symposium K will be held on Tu, April 5 and We, April 6. The
conference will also include other symposia on following topics:
- General Systems Methodology
- Designing and Systems
- Humanity, Architecture and Conceptualisation
- Cybernetics in Biology and Medicine
- Cybernetics of Socio-Eonomic Systems
- Fuzzy Sets and Systems
- Computer-Aided Systems Theory
- Robotics and Flexible Manufacturing
- Systems Engineering for Peace Research
- Artificial Intelligence
- Innovation Systems in Business and Administration
- The Management and Cybernetics of Organizations
- Communication and Computers
Conference Fee: AS 2,900 (incl.proceedings - 2 volumes). The
proceedings will also be available from Kluwer Academic
Publishers, Dordrecht/Boston/Lancaster/Tokyo, with the title
"Cybernetics and Systems '88"
If you want to participate or to get further information, write
to:
EMCSR Conference Secretariat
Austrian Society for Cybernetic Studies
Schottengasse 3
A-1010 Vienna, Austria
Tel: +43 222 535 32 810
Email: A5421DAA@AWIUNI11.BITNET
------------------------------
Date: Mon, 11 Apr 88 13:37:37 CDT
From: Lugowski@RESBLD
Subject: Neural Network research in Japan. Conference program
Dear Colleagues:
Resurgence of neural network research in Japan seemed to have
started this spring. Many seminars and lectures are held since
last December. I'd like to show the situation by introducing
related conference programs in this spring. I hope this will
give you some understanding of Neural Network research in Japan.
Followings are excerpts from the conference programs of
(1) The Institute of Electronics, Information and Communication
Engineers (biggest society for electrical engineers), and
(2) The Acoustical Society of Japan.
There are another conferences and technical meetings relating
neural network research in this spring. I think I can introduce
them later.
We have also presented our research at the A.S.J. Technical meeting
on hearing last week. The title is:
%A Hideki Kawahara
%A Toshio Irino
%T Temporal Feature Extraction using State Compression Neural
Networks: Application to Speech Perception Study
%R H-88-15, the Acoustical Society of Japan
%D 1988 March 14
This report will present a new insight on the relation between
Tank & Hopfield's and Stornetta's method of temporal feature
manipulation and on temporal characteristics of human auditory
systems. I'd like to introduce this after completing additional
experiments and translation into English.
-- Hideki Kawahara
NTT Basic Research Laboratories
3-9-11 Midori
Musashino, Tokyo 180, Japan
PS: Excuse me for delay in sending our previous research reports.
Your request is kept in our mailing list. The English version will
come out by the end of April. (I hope)
---- list starts ------
-----------------------
Spring Annual Meeting of the IEICE '88
29-31/March/1988 Tokyo
*** Session A *****
%A Ken-ichi Iso
%A Takao Watanabe
%T Correction of Phoneme Recognition Errors by Artificial Neural Network
%O C&C Information Technology Research Laboratories, NEC Corporation
*** Session D *****
%A Eiji Takimoto
%A Masayuki Kimura
%T Non-supervised Learning Model for Temporal Patterns
%O Faculty of Engineering, Tohoku University
%A Masaaki Mihara
%A Toshifumi Kobayashi
%A Michihiro Yamada
%T An Approach to the Associative Memory with Crosstalk Reduction
%O LSI R&D Laboratory Mitsubishi Electric Corporation
%A Noboru Katta
%A Hideya Takahashi
%A Eiji Shimizu
%T Relational Matching using a Neural Network
%O Faculty of Engineering, Osaka University
%A Itsuo Kumazawa
%A Hidemitsu Ogawa
%T Neural-nets whose Atractors are Separated with Long Hamming Distances
from Each Other
%O Tokyo Institute of Technology, Department of Computer Science
%A Itsuo Kumazawa
%A Kazutaka Yamasaki
%A Hidemitsu Ogawa
%T Constraints Satisfaction Searches using Atractors with Long Hamming
Distances from Each Other
%O Tokyo Institute of Technology, Department of Computer Science
%A Keiko Minami
%A Ikuo Matsuba
%T Neural Network Approach to Image Reconstruction
%O Systems Development Laboratory, Hitachi, Ltd.
%A Hideki Asoh
%T A Model of Concepts Formation with Boltzmann Machine
%O Electrotechnical Laboratory
%A Masanori Izumida
%A Kenji Murakami
%A Tsunehiro Aibara
%T Fuzzy Clustering on Hopefield Model
%O Faculty of Engineering, Ehime University
%A Yoshimasa Kimura
%A Tadasu Uchiyama
%T An Analysis of PDP model with Back-Propagation Learning Algorithm
%O NTT Human Interface Laboratories
%A Katsunori Shimohara
%A Yukio Tokunaga
%A Tadasu Uchiyama
%A Takaya Endo
%T Sequential Processing PDP Model with Back-propagation Algorithm -
Model-categolization and Considerations -
%O NTT Human Interface Laboratories
%A Katsunori Shimohara
%A Tadasu Uchiyama
%A Yukio Tokunaga
%T Sequential Processing PDP Model with Back-propagation Algorithm -
Application for a Feed-back Circuit -
%O NTT Human Interface Laboratories
%A Katsunori Shimohara
%A Tadasu Uchiyama
%A Yukio Tokunaga
%T Sequential Processing PDP Model with Back-propagation Algorithm -
Application for a Combinational Retrieval Problem -
%O NTT Human Interface Laboratories
%A Tadasu Uchiyama
%A Katsunori Shimohara
%A Yukio Tokunaga
%T Sequential Processing PDP Model with Back-propagation Algorithm -
Application for Recognition of Periodicity in Sequential Data -
%O NTT Human Interface Laboratories
%A Yoshihiro Mori
%A Kazuhiko Yokosawa
%A Michio Umeda
%T An Application of PDP Model to Similar Kanji Character Discrimination
%O ATR Auditory and Visual Perception Research Laboratories
%A Hideyo Morita
%A Takahide Matsuoka
%T On the Signal Transmission by Use of IPFM with a Refactory Period
%O Utsunomiya University
%A Shiro Usui
%A Akiyuki Anzai
%A Yoshimi Kamiyama
%A Sei Miyake
%T Development and Application of Neural Circuit Simulator
%O Toyohashi University of Technology, Department of Information &
Computer Science. (1st to 3rd auther) ATR Auditory and Visual Perception
Research Laboratories
%A Katsuhiro Kamada
%A Yuzo Hirai
%T Digital Neuron Model
%O University of Tsukuba
%A Ikuo Matsuba
%A Keiko Minami
%T State-dependent Simulated Annealing
%O Systems Development Laboratory, Hitachi, Ltd.
%A Takeshi Yamamoto
%A Hirofumi Nagashino
%A Yohsuke Kinouti
%A Tomiyuki Ushita
%T Analysis of a Self-Organizing Neural Network Model with Backward
Inhibition
%O The University of Tokushima
%A Tadayuki Sakakibara
%A Kunio Onda
%A Yosinao Aoki
%T Examination of Movement Learning Method using Cerebellar Model
%O Hokkaido University
%A Yutaka Ooyatsu
%A Kazuo Horiuti
%T Analysis on a Model of Associative Memory with Learning Function
%O School of Science and Engineering, Waseda University
%A Katsumasa Haneta
%T An Analysis of Characteristic of Human Memory Retrieving
%O Koryo Junior High School
%A Yasurou Odaka
%A Haruhisa Takahashi
%A Etsuji Tomita
%T Learning in a Stochastic Neural Network with Error Propagation
%O Dept. of Communication & System, University of Electro-Communications
%A Akihiko Machizawa
%T A Study on Retinal Model for Color Signal
%O Radio Research Laboratory, Ministry of Posts and Telecommunication
%A Masahiro Nishino
%A Katsumi Yoshine
%A Naohiro Ishii
%T Measurement of Wiener Kernels in Catfish Retina by Spike Train
and Slow Potential
%O Nagoya Institute of Technology
%A Tomoo Sato
%A Yasumitu Miyazaki
%A Hiroji Kutiwaki
%T A Photochemical Measurement of the Action Potential in Brain
using Laser Beam
%O Toyohashi University of Technology (1st and 2nd auther) and
Nagoya University, School of Medicine (3rd auther)
***** Special Session GD *******
%A Kunihiko Fukushima
%T Trend in Neural Network Models
%O NHK Science and Technical Research Laboratories
%A Mitsuo Kawato
%T Status and Perspective of Neural networks
%O Department of Biophysical Engineering, Faculty of Engineering
Science, Osaka University
%A Hideaki Saito
%T Neural Mechanism and Neuro-Computers
%O NHK Science and Technical Research Laboratories
%A Yoichi Muraoka
%T Parallel Processing and Neural Computers
%O School of Science and Engineering, Waseda University
%A Hiroo Yonezu
%T Neural Computing Devices
%O Toyohashi University of Technology
%A Koji Kurata
%T Real-Valued Boltzmann Machines
%O University of Tokyo
%A Shiro Usui
%T Parallel Processing and Early Vision
%O Information and Computer Science, Toyohashi University of
Technology
***** Special Session SD ******
%A Tadashi Ae
%A Reiji Aibara
%T Massive Parallelism of a Neurocomputer and its Realization
%O Faculty of Engineering, Hiroshima University
--------------------------------------------------------------------
Spring Annual Conference of the Acoustical Society of Japan '88
23-25/March/1988 Tokyo
**** Session Speech(A) ******
%A Kou-jian Li
%A Fumitada Itakura
%T Adaptation of Multiple Regression Coefficients and Recognition
of Chinese Four Tones
%O School of Engineering, Nagoya University
**** Poster Session Speech **********
%A Ken-ichi Iso
%A Takao Watanabe
%T Phoneme Labeling by Neural Networks
%O NEC Corporation
%A Masami Nakamura
%A Kiyohiro Shikano
%T A Study of Word Category Prediction by Connectionist Models
%O ATR Interpreting Telephony Research Laboratories
%A Ken-ichi Funahashi
%T Vowel Recognition in Word Utterances by Neural Networks
%O ATR Auditory and Visual Perception Research Laboratories
%A Tatsuo Matsuoka
%A Hiroshi Hamada
%A Ryouhei Nakatsu
%T A Study on Syllable Recognition using Neural Networks
%O NTT Human Interface Laboratories
%A Hideyuki Takagi
%A Eiichi Tuboka
%T Pseudo-Formant Extraction by Neural Net
%O Matsushita Electric Industrial Co., LTD
%A Hideyuki Takagi
%A Noriyo Hara
%T Prosody Control by Neural Net -- A Case of Pitch Control --
%O Matsushita Electric Industrial Co., LTD
%A Shin'ichi Tamura
%A Alex Waibel
%T Noise Reduction Through Waveform Input and Output using Neural
Networks
%O ATR International Telephony Research Laboratories
%A Noboru Kanedera
%T Phonetic Segmentation using Neural Network
%O Ishikawa College of Technology
%A Toshio Irino
%A Hideki Kawahara
%T Vowel Feature Extraction from Cochlear Vibration by Neural
Networks - Exploring Speech Representations using Neural Networks -
%O NTT Basic Research Laboratories
---------------------
PS1:
Unfortunately, almost all of these materials are written in Japanese.
Some of the authors will attend ICNN, INSS, ASA and NIPS. Then you
can exchange information there.
PS2:
I will also attend the ASA meeting in Seattle 16-21 May. I'm looking
forward to seeing you and having discussion.
------------------------------
End of NEURON-Digest
********************
