From crabapple.srv.cs.cmu.edu!cantaloupe.srv.cs.cmu.edu!rochester!rutgers!usc!math.ohio-state.edu!darwin.sura.net!newsserver.jvnc.net!yale.edu!xlink.net!gmd.de!eddi Mon Aug 16 13:04:46 EDT 1993
Article: 18376 of comp.ai
Xref: crabapple.srv.cs.cmu.edu comp.ai:18376 comp.ai.shells:1179
Path: crabapple.srv.cs.cmu.edu!cantaloupe.srv.cs.cmu.edu!rochester!rutgers!usc!math.ohio-state.edu!darwin.sura.net!newsserver.jvnc.net!yale.edu!xlink.net!gmd.de!eddi
From: eddi@gmd.de (Edgar Sommer)
Newsgroups: comp.ai,comp.ai.shells
Subject: Mobal2.2 available via FTP
Keywords: knowledge acquisition, machine learning
Message-ID: <eddi.745490040@gmd.de>
Date: 16 Aug 93 08:34:00 GMT
Sender: news@gmd.de (USENET News)
Organization: GMD, Sankt Augustin, Germany
Lines: 124
Nntp-Posting-Host: gmdzi


Dear Netter,

The knowledge acquisition and machine learning system MOBAL (release 2.2)
is available free  for non-commercial  academic  use from  the  anonymous
ftp-server 'ftp.gmd.de'  in  the directory  'gmd/mlt/Mobal'.  The  system
requires a  Sun  SparcStation, SunOS 4.1,  OpenWindows 2.0, and HyperNeWS
1.4; the  latter can be obtained by sending mail to newsdev@turing.ac.uk.
By  agreement with  Turing Institute, HyperNeWS 1.4 is now also available
from our server in the directory 'gmd/mlt/HyperNeWS'.


About MOBAL
-----------
Mobal is  a  sophisticated system  for  developing operational  models of
application  domains. It integrates  a  manual  knowledge acquisition and
inspection environment,  a  powerful inference  engine, machine  learning
methods  for automated knowledge acquisition, and  a  knowledge  revision
tool.

By using Mobal's knowledge acquisition environment, you can incrementally
develop a model of  your domain  in terms of logical facts and rules. You
can inspect the  knowledge you have entered  in text or graphics windows,
augment the  knowledge, or change it at any time.  The built-in inference
engine can immediately execute the rules you have entered to show you the
consequences  of  your  inputs,  or  answer  queries  about  the  current
knowledge.  Mobal also builds a dynamic sort taxonomy from  your  inputs.
If  you wish,  you can use  machine  learning  methods  to  automatically
discover additional rules based on the facts that you have entered, or to
form new concepts.  If there are contradictions in the knowledge base due
to  incorrect rules or facts,  there is a knowledge revision tool to help
you locate the problem and fix it.


Changes since Mobal 2.0 
----------------------- 
MOBAL release  2.2  offers some interesting new  features and a number of
small improvements making it worth  your  while to replace older releases
of the system.

1. MOBAL as an ILP toolbox

Since the very first releases, MOBAL has been a kind  of toolbox offering
different tools  (including  the Rule Discovery Tool RDT)  to support the
modeling of  domains.   Now  we  have coupled MOBAL with some other  well
known ILP systems. The new release contains interfaces to and the code of
following learning systems:

    - FOIL 5 (J. Ross Quinlan),
    - GOLEM  (S. Muggelton and C. Feng),
    - mFOIL  (S. Dzeroski and I. Bratko),
    - CILGG  (J.-U. Kietz), and
    - INCY   (E. Sommer).

Many thanks to the authors of the programs  for their  kind permission to
include the systems in the new release!

The user can select any of these tools (and RDT, of course) within MOBAL.
The  knowledge base is automatically  translated into the format required
by the called algorithm and the resulting rules are translated back  into
MOBAL's  format. As  the coupling is  achieved  by defining  input/output
filters  for each tool,  third party implementations can  be used without
modifications.  Furthermore,  MOBAL  2.2  is  open to be coupled to other
learning systems.

2. Integrity Constraints

The new release offers the  possibilty  to  state  integrity constraints.
MOBAL checks whether all constraints are satisfied either continuously or
on  demand.  Violations  are placed  on the system's  agenda  and can  be
resolved by the user at a convenient time.

3. Programmer's Interface

MOBAL 2.2 includes a  Programmer's Interface,  which gives  access to the
full  range of MOBAL's knowledge representation and inference,  knowledge
acquisition and learning facilities.


User Guide
----------
MOBAL's  User  Guide has  completely reworked  and  extended for the  new
release.   A  compressed PostScript  version  can  be found in the  MOBAL
directory

Acknowledgements
----------------
Mobal 2.2 is a result of research funded by  the Euopean Community within
the type B ESPRIT Project 2154 "Machine Learning Toolbox"  and the ESPRIT
Project "Inductive Logic  Programming" (ILP, PE 6020) and is based on the
Sytem BLIP developed in  the project "Lerner" at the Technical University
Berlin funded by the German government (BMFT) under contract ITW8501B1.

Mobal is being developed with Quintus Prolog 3.1.1 on a Sun4.   We  would
like  to thank the Quintus Corporation  for their support in making  this
runtime version of MOBAL possible.


Restrictions 
------------ 
MOBAL is  available in the hope that  it will be useful,  but WITHOUT ANY
WARRANTY; without even  the implied warranty  of FITNESS FOR A PARTICULAR
PURPOSE.

MOBAL  can  be  used  free  of  charge  for  academic,  educational,   or
non-commercial uses.  We  do  require,  however,  that you send  us  mail
(addresses below)  so we know where MOBAL is  going.  This  will also get
you  access to MobalNews, our mailing  list where we  let all  registered
MOBAL users know about updates, bug fixes, etc.


Cheers,
the MLT team

-----------
Project MLT
GMD (German National Research Center for Computer Science)
AI Research Division (I3.KI)
Schloss Birlinghoven
D 53757 St. Augustin 
Germany

Fax:    +49/2241/14-2889
E-Mail: mobal@gmdzi.gmd.de


