NetNews Usenet Archive 1993 #3/NN_1993_3.iso/spool/comp/ai/4958

Text File | 1993-01-21 | 7.4 KB | 155 lines

Newsgroups: comp.ai
Path: sparky!uunet!gatech!destroyer!cs.ubc.ca!unixg.ubc.ca!kakwa.ucs.ualberta.ca!alberta!arms
From: [e-mail] (Bill Armstrong)
Subject: ALN patent expires
Message-ID: <arms.727650547@spedden>
Summary: Patent on adaptive logic networks expired on Jan. 20, 1993.
Keywords: adaptive logic network
Sender: [e-mail] (News Administrator)
Nntp-Posting-Host: spedden.cs.ualberta.ca
Organization: University of Alberta, Edmonton, Canada
Date: Thu, 21 Jan 1993 21:09:07 GMT
Lines: 141

After 17 years, the U.S. patent on adaptive logic networks has run its
course, and the material covered by the patent is now in the public
domain, free for anyone to use without paying:

  W. Armstrong, Adaptive Boolean Logic Element, U. S. Patent 3934231,
  filed Feb. 28, 1974 (filings in various other countries followed),
  patent granted on Jan. 20, 1976, assigned to Dendronic Decisions
  Limited, now located at 3624 - 108 Street, Edmonton, Alberta, T6J 1B4,
  Tel.  [phone].

The patent covered what is essentially the backpropagation algorithm
for training logic networks, except that in the ALN context it was
called "heuristic responsibility".  There were actually three kinds of
heuristic responsibility covered, one of which was a steepest descent
approach corresponding almost directly to backprop.  It was found not
to work very well.  It would end to get stuck at local minima of
error.  Two other algorithms were given, called "latest error" and
"global search" which worked much better.  There are still traces of
the "latest error" heuristic in the atree release 2.7 software for
Windows 3.x and atree release 2.0 for Unix.  The latter programs use
the same adaptation algorithm; the advantage of 2.7 is that it has
extensive on-line documentation, while the advantage of atree 2.0 is
portability.

The patent had three constructive reductions to practice in an effort
to be *generic*, i.e. to cover *everything* which was a case of
heuristic responsibility.  The last claim covered a digital logic
circuit having elements with "heuristic responsibility" leads.  As a
consequence of the expiration, one can hope that a large part of ALN
technology will end up in the public domain.  Of course it is still
possible to patent improvements, but these can only be non-obvious
ones.

As many people have discovered, ALNs learn and execute very quickly.
In fact, they are at the very limits of speed for digital logic
circuits.  This means that they will be around for a long time.

Well over 5000 people have obtained the software on Internet or
CompuServe, and some interesting applications have been done.

Those who are interested in this approach to high speed neural
networks can get the the atree adaptive logic network simulation
package as follows (N. B. the expiration of the patent has nothing to
do with the copyright on the atree software, which has not expired!):

The atree adaptive logic network (ALN) simulation package, atree
release 2.7, is available via anonymous ftp from menaik.cs.ualberta.ca
[129.128.4.241] in pub/atre27.exe (ftp in binary mode).  It runs on
IBM PCs and compatibles under Windows 3.x. Included is documentation
and ON-LINE HELP explaining the basic principles of adaptive logic
networks, the atree source code and the examples.  All C and C++
source code is provided.

Atree release 2.7 is available in either of two files in pub/ on
menaik: atre27.exe and a27exe.exe.  The file atre27.exe contains the
full C and C++ sources for those who want to study or modify them. The
code was developed using Borland C++ 3.1 and Application Frameworks.
The other, smaller file contains just the executables. The user can
study the adaptive algorithm in the On-Line Help under ALN Technical
Notes/The Learning Algorithm.

To set up your software on the PC under Windows 3.x, it is recommended
that you execute atre27.exe in your main directory, whereupon it will
create a subdirectory atree_27 and extract everything into it.
Running "setup" in the latter directory will create a group of icons
you can use to invoke demos and the facilities for programming
adaptive logic network applications in the lf language.  The "Open"
command gives you access to numerous instructive examples.  Clicking
on the Help button gives you access to explanations of theory and
code.

The Unix version, atree release 2.0, is in C, and has been ported to
Macintosh, Amiga, and other machines.  Windows NT will eventually
offer another way to use atree on various platforms.

There is an electronic mailing list for discussions of ALNs. Mail to
[e-mail] to subscribe or cancel.  Your comments on
ALN subjects can be emailed to all other subscribers to the list by
mailing to [e-mail].

        A BIBLIOGRAPHY

G. v. Bochmann, W. Armstrong, Properties of Boolean Functions
with a Tree Decomposition, BIT 13, 1974. pp. 1-13.

W. Armstrong, Gilles Godbout: Use of Boolean Tree Functions to Perform
High-Speed Pattern Classification and Related Tasks, Dept. d'IRO,
Universite de Montreal, Doc. de Travail #53, 1974. (unpublished,
except in summary form as follows:)

W. Armstrong and G. Godbout, Properties of Binary Trees
of Flexible Elements Useful in Pattern Recognition, IEEE 1975
International Conf. on Cybernetics and Society, San Francisco, 1975,
IEEE Cat. No. 75 CHO 997-7 SMC, pp. 447-449.

W. Armstrong and J. Gecsei, Architecture of a Tree-based
Image Processor, 12th Asilomar Conf. on Circuits, Systems
and Computers, Pacific Grove, Calif., 1978, pp. 345-349.

W. Armstrong and J. Gecsei, Adaptation Algorithms for
Binary Tree Networks, IEEE Trans. on Systems, Man and
Cybernetics, 9, 1979, pp. 276-285.

W. Armstrong, J.-D. Liang, D. Lin, S. Reynolds, Experiments Using
Parsimonious Adaptive Logic, Tech. Rept. TR 90-30, Department of
Computing Science, University of Alberta, Edmonton, Alberta, Canada,
T6G 2H1.  This is now available in a revised form via anonymous FTP
from menaik.cs.ualberta.ca [129.128.4.241] in pub/atree2.ps.Z (the
title of the revised document is Some Results concerning Adaptive
Logic Networks).

W. Armstrong, A. Dwelly, J.-D. Liang, D. Lin, S. Reynolds, Learning
and Generalization in Adaptive Logic Networks, in Artificial Neural
Networks, Proceedings of the 1991 International Conference on
Artificial Neural Networks ( ICANN'91), Espoo,
Finland, June 24-28, 1991, T. Kohonen, K.Makisara, O. Simula, J. Kangas eds.
Elsevier Science Publishing Co. Inc. N. Y. 1991, vol. 2, pp. 1173-1176.

Allen G. Supynuk, William W. Armstrong, Adaptive Logic Networks and
Robot Control, Proc. Vision Interface Conference '92, also called
AI/VI/GI '92, Vancouver B. C., May 11-15, 1992, pp. 181 - 186.

R. B. Stein, A. Kostov, M. Belanger, W. W. Armstrong and D. B.
Popovic, Methods to Control Functional Electrical Stimulation in
Walking, First International FES Symposium, Sendai, Japan, July 23 -
25, 1992, pp. 135 - 140.

Aleksandar Kostov, Richard B. Stein, William W. Armstrong, Monroe
Thomas, Evaluation of Adaptive Logic Networks for Control of Walking
in Paralyzed Patients, 14th Ann. Int'l Conf. IEEE Engineering in
Medicine and Biology Society, Paris, France, Oct. 29 - Nov. 1, 1992,
pp. 1332 - 1334.

Ian Parsons, W. W. Armstrong: The Use of Adaptive Logic Nets to
Quantify Tar Sands Feed (Draft), available via anonymous ftp from
menaik.cs.ualberta.cs [129.128.4.241] in pub/alntarsands.ps.Z.
--
***************************************************
Prof. William W. Armstrong, Computing Science Dept.
University of Alberta; Edmonton, Alberta, Canada T6G 2H1
[e-mail] Tel[phone] FAX [phone]