The Cognitive Computation Group at the University of Illinois at
Urbana/Champaign announces the release of the SNoW Learning
Architecture (version 2.0).
SNoW is a learning program that can be used as a general purpose
multi-class classifier and is specifically tailored for learning in
the presence of a very large number of features. The learning
architecture is a sparse network of linear units over a pre-defined
or incrementally acquired feature space. Several update rules may be
used - sparse variations of the Winnow update rule, Perceptron, or
naive Bayes.
SNoW has been used successfully in several applications in the
natural language and visual processing domains; the release is meant
to be used only for research purposes, with the hope that it can be a
useful research tool for studying learning in these domains.
Feedback of any sort is welcome.
You are invited to download the SNoW package for educational or
non-commercial research purposes. When downloading the package you
are asked to register and express your agreement with the license
terms, under the university of Illinois guidelines. SNoW is not
shareware or public domain software.
The SNoW software package can be downloaded by following the
`Software' link under the Cognitive Computation group home page at
http://L2R.cs.uiuc.edu/~cogcomp
The SNoW package contains the following:
- Source code (C++) with a Makefile.
- A user guide (UIUC Tech Report, UIUC-DCS-R-99-210) containing brief
description of the architecture and algorithms, detailed
descriptions of the command-line options, and a brief tutorial.
- The text of the license agreement.
Two packages are available, one for UNIX system (that should be
easily installed also on most Linux systems) and a second for NT
systems.
The User guide (UIUC Tech report UIUC-DCS-R-99-210, by Andrew
J. Carlson, Chad M. Cumby, Jeff L. Rosen and Dan Roth) can be
downloaded directly from:
http://L2R.cs.uiuc.edu/~danr/Papers/userguide.ps.gz
Papers related to SNoW can be found at
http://L2R.cs.uiuc.edu/~danr/snow.html
For comments and bug reports relating to SNoW, please send mail to
----------------------------------------------------------------------
Dan Roth
Department of Computer Science, University of Illinois, Urbana/Champaign
1304 W. Springfield Ave. Urbana IL 61801
Phone: (217) 244-7068 (217) 244-6813 (Sec) Fax: +(217) 244-6500
e-mail: danr@cs.uiuc.edu http://L2R.cs.uiuc.edu/~danr
----------------------------------------------------------------------