Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news4.ner.bbnplanet.net!news.ner.bbnplanet.net!howland.reston.ans.net!EU.net!chsun!idsia.ch!juergen
From: juergen@idsia.ch (Juergen Schmidhuber)
Subject: neural net postdoc position -- URGENT
Message-ID: <DMIH40.9rs@eunet.ch>
Keywords: unsupervised learning
                        +------------------+
                        | POSTDOC POSITION |
                        +------------------+
Sender: usenet@eunet.ch
Organization: Istituto Dalle Molle di Studi sull'Intelligenza Artificiale
Date: Fri, 9 Feb 1996 13:50:23 GMT
Lines: 59

IDSIA may soon (within a few months) be able to offer a postdoc 
position for a 2-year research project. Goal is to analyze, 
compare, extend, and apply ``neural'' algorithms for unsupervised 
learning and redundancy reduction. One focus will be on the recent 
technique ``predictability minimization'' (see references below). 
Application areas include adaptive image pre-processing, classification, 
data compression. We are looking for someone with experience in such 
areas.

IDSIA is located in scenic Lugano (Switzerland). Check out my 
home page. CSCS, the Ticino supercomputing center, is nearby.  
Salary is competitive.

Once the project is approved, there will be a separate announcement.  
The potential funder of this project, however, wants to see candidate 
names by 

                    MONDAY, FEBRUARY 12, 1996.  
	     
Sorry for not posting earlier - I became aware of this today. I hope 
this message will reach you in time. If interested, send *brief* CV, 
list of publications, and *brief* cover letter with statement of 
research interests to 

                       juergen@idsia.ch

Send them as separate, uncompressed ASCII or postscript files. Call
the subject headers of ASCII files name.cv, name.pub, name.cover, 
respectively, where ``name'' stands for your name. Call the subject 
headers of postscript files name.cv.ps, name.pub.ps, name.cover.ps, 
respectively. Thanks a lot!

Juergen
 
------------------------ RECENT REFS -------------------------

J. Schmidhuber,  M. Eldracher, and B. Foltin.
Semilinear predictability minimization produces well-known
feature detectors.  Accepted by Neural Computation, 1995.

J. Schmidhuber and D. Prelinger.  Discovering predictable 
classifications.  Neural Computation, 5(4):625--635, 1993.

J. Schmidhuber.  Learning factorial codes by predictability 
minimization.  Neural Computation, 4(6):863--879, 1992.


+-----------------------------------------------------+
| Juergen Schmidhuber,              research director |
| IDSIA,   Corso Elvezia 36, 6900-Lugano, Switzerland |
+-----------------------------------------------------+
| juergen@idsia.ch       http://www.idsia.ch/~juergen |
+-----------------------------------------------------+

                        +------------------+
                        | POSTDOC POSITION |
                        +------------------+
 

