Newsgroups: comp.ai.jair.announce
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!newsfeed.cit.cornell.edu!news.tc.cornell.edu!newsserver.sdsc.edu!news.cerf.net!mvb.saic.com!news.mathworks.com!newsfeed.internetmci.com!news.msfc.nasa.gov!pendragon.jsc.nasa.gov!ames!eos!kronos.arc.nasa.gov!jair-ed
From: jair-ed@ptolemy.arc.nasa.gov
Subject: New Article, Diffusion of Context and ...
Message-ID: <1995Oct31.212150.22372@ptolemy-ethernet.arc.nasa.gov>
Originator: jair-ed@polya.arc.nasa.gov
Lines: 49
Sender: usenet@ptolemy-ethernet.arc.nasa.gov (usenet@ptolemy.arc.nasa.gov)
Nntp-Posting-Host: polya.arc.nasa.gov
Organization: NASA/ARC Computational Sciences Division
Date: Tue, 31 Oct 1995 21:21:50 GMT
Approved: jair-ed@ptolemy.arc.nasa.gov

JAIR is pleased to announce the publication of the following article:

Bengio, Y. and Frasconi, P. (1995)
  "Diffusion of Context and Credit Information in Markovian Models", 
   Volume 3, pages 249-270.
   PostScript: volume3/bengio95a.ps (397K)
	       compressed, volume3/bengio95a.ps.Z (158K)


   Abstract: This paper studies the problem of ergodicity of transition
   probability matrices in Markovian models, such as hidden Markov models
   (HMMs), and how it makes very difficult the task of learning to
   represent long-term context for sequential data.  This phenomenon
   hurts the forward propagation of long-term context information, as
   well as learning a hidden state representation to represent long-term
   context, which depends on propagating credit information backwards in
   time.  Using results from Markov chain theory, we show that this
   problem of diffusion of context and credit is reduced when the
   transition probabilities approach 0 or 1, i.e., the transition
   probability matrices are sparse and the model essentially
   deterministic.  The results found in this paper apply to learning
   approaches based on continuous optimization, such as gradient descent
   and the Baum-Welch algorithm.

The PostScript file is available via:
   
 -- comp.ai.jair.papers

 -- World Wide Web: The URL for our World Wide Web server is
       http://www.cs.washington.edu/research/jair/home.html

 -- Anonymous FTP from either of the two sites below:
      CMU:   p.gp.cs.cmu.edu        directory: /usr/jair/pub/volume3
      Genoa: ftp.mrg.dist.unige.it  directory:  pub/jair/pub/volume3

 -- automated email. Send mail to jair@cs.cmu.edu or jair@ftp.mrg.dist.unige.it
    with the subject AUTORESPOND, and the body GET VOLUME3/FILE-NM
    (e.g., GET VOLUME3/MOONEY95A.PS)
    Note: Your mailer might find our files too large to handle. Also, note  
    that compressed files cannot be emailed, since they are binary files.

 -- JAIR Gopher server: At p.gp.cs.cmu.edu, port 70. 

For more information about JAIR, check out our WWW or FTP sites, or
send electronic mail to jair@cs.cmu.edu with the subject AUTORESPOND
and the message body HELP, or contact jair-ed@ptolemy.arc.nasa.gov.



