Knowledge Discovery Nuggets Index


To
KDNuggets Directory   |   Here is how to subscribe to KD Nuggets   |   This Year   |   Past Issues

Knowledge Discovery Nuggets(tm) 98:6, e-mailed 98-03-15


News:
  • (text) GPS, KDNuggets 1 year anniversary and New Submission Guidelines
    www.kdnuggets.com/news/submissions.html
  • (text) Sreerama K. Murthy, PC Week: Mining for intelligence without a shovel,
    http://www.zdnet.com/pcweek/opinion/0302/02wide.html
  • (text) Alex Chelminsky, BusinessWire: ISL and SPSS Partnership
  • (text) Tej Anand, Now Golden Books Family Entertainment CIO
  • (text) Alex Chelminsky, Information Week: Data Mining at GM

    Publications:
  • (text) David Hatter, Proposed book on Data Mining -- feedback solicited
  • (text) Ryszard S. Michalski, New Book: Machine Learning & Data Mining,
    http://www.wiley.com/ordering/
  • (text) Maria Zemankova, Digital Libraries Initiative - Phase 2
    http://www.nsf.gov/home/crssprgm/dli/start.htm
  • (text) N. Gershon, Call for Papers, Journal of Intelligent Information Systems
    Special Issue on INFORMATION VISUALIZATION,
    http://www.isse.gmu.edu/JIIS/

    Positions:
  • (text) Ross Donald King, UK-Wales: Data Mining Ph.D. Studentships
    http://www.aber.ac.uk/~dcswww/Research/bio/
  • (text) Hal Duncan, US-California: RESEARCH PROGRAMMERS, NASA AMES

    Courses:
  • (text) Rob Gerritsen, Exclusive Ore Data Mining Seminar,
    April 22, Conshohocken, PA, http://www.xore.com

    Meetings:
  • (text) Alex H B Duffy, Call for Papers, Workshop on Machine Learning in Design,
    Portugal, July 1998
    http://www.cad.strath.ac.uk/~alex/AID/AID98/AID98-MLinD.html
  • (text) Riccardo Bellazzi, IDAMAP-98: ECAI Workshop: a reminder
    http://aim.unipv.it/~ric/idamap98
    --
    latest news, publications, tools, meetings, and other relevant items
    in the Data Mining and Knowledge Discovery field.
    KD Nuggets is currently reaching over 4500 readers in 60+ countries
    twice a month.

    Submissions relevant to data mining and knowledge discovery are welcome
    and should be emailed to gps in ASCII text or HTML format.
    See www.kdnuggets.com/news/submissions.html for submission guidelines.
    A submission should have a subject line which clearly describes
    what is it about. Please keep calls for papers and meeting announcements
    short, and provide a web site for details. Submissions may be edited for size.

    To subscribe, see www.kdnuggets.com/news/subscribe.html

    Back issues of KDNuggets, a catalog of data mining tools
    ('Siftware'), pointers to data mining companies, relevant websites,
    meetings, and more is available at KDNuggets Directory at
    http://www.kdnuggets.com/

    -- Gregory Piatetsky-Shapiro (editor)
    gps

    ********************* Official disclaimer ***************************
    All opinions expressed herein are those of the contributors and not
    necessarily of their respective employers (or of KD Nuggets)
    *********************************************************************

    ~~~~~~~~~~~~ Quotable Quote ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    From Salon http://www.salon1999.com/ Haiku error message contest
    Printer not ready.
    Could be a fatal error.
    Have a pen handy?


    Previous  1 Next   Top
    Date: Sun, 15 March 1998 10:41:10 -0500 (EST)
    From: GPS gps
    Subject: KDNuggets 1-year anniversary and New Submission Guidelines

    It has been slightly over one year of independent operation for kdnuggets newsletter
    and kdnuggets.com website. In the last year KDNuggets subscriber base grew from
    2771 on February 28, 1997 to 4606 email addresses on March 1, 1998 to over 60
    countries from 5 continents.

    Domain/Region Count Percentage
    USA com 1757 38.1
    USA edu 609 13.2
    USA-other 444 9.6
    Canada 105 2.3
    West Europe 981 21.3
    East Europe 81 1.8
    Asia 75 1.6
    Pacific Rim 378 8.2
    Latin America 94 2.0
    Middle East 49 1.1
    Africa 31 0.7
    Other 2 0.0

  • The associated KDNuggets website

  • has received over 380,000 hits between March 1997 and March 1998 and has
    served over 2.5 Gigabytes of data.

    Given the increasing cost and effort required to maintain KDNuggets,
    KDNuggets will start charging a modest fee for placing commercial messages
    (such as product or service announcements, courses, job positions),
    beginning March 15, 1998.
    The fee will be $100 for messages up to 50 lines (each line up to 80-characters),
    $200 for messages up to 100 lines, and $300 for messages up to 150 lines.
    The commercial message will included in Nuggets
    upon sender acceptance of the above rate, and the sender will receive the invoice
    for the appropriate amount.

    News, publications, research meetings, and other messages which are not directly
    advertising a commercial product or service will continue to be included free
    of charge. However, please keep those messages,
    especially calls for papers and meeting announcements brief
    (50 lines of text up to 80 characters each) and provide a web site for details.
    Longer messages may be edited and shortened.
    Meeting announcements and calls for papers that are directly relevant
    (i.e. do not have data mining or
    knowledge discovery or equivalent keywords among the main topics)
    will not be included in KDNuggets.

    Please send any questions to the KDNuggets editor at

  • gps.




  • Previous  2 Next   Top

    Date: Fri, 06 Mar 1998 10:09:01 -0500
    From: 'Dr. Sreerama K. Murthy' murthy@scr.siemens.com
    Subject: PC WEEK: Mining for intelligence without a shovel

  • From http://www.zdnet.com/pcweek/opinion/0302/02wide.html





  • PC WEEK: Mining for intelligence without a shovel

    Mining for intelligence without a shovel

  • By John Taschek



  • 03.02.98





    It seems as if U.S. Intelligence forces will do anything to get enough data to prove that Iraq is making chemical weapons, including going to war. Companies seeking good data that will give them a competitive edge also have their battles to fight.


  • IBM's massive business intelligence announcements last week are meant to show that companies can arm themselves for battle. But before anyone gets carried away, there are a couple of fundamental questions everyone should ask: Who, exactly, stands to benefit from business intelligence tools, and will they even work?


  • "Business intelligence" is another of those randomly created terms that defines the set of tools and services for getting and analyzing data. Some analysts lump everything from spreadsheets to report writers into the BI market. But I'll take the high road on this one and narrow the field to higher-end products from OLAP to data mining tools.


    Either way, BI is a humongous, multibillion-dollar market. IBM considers it one of the company's five major initiatives this year, right in there with year 2000, electronic commerce, big-iron servers and packaged enterprise resource planning applications.


    Study them carefully, though, and you'll see that the IBM announcements are basically about a couple of upgraded tools and a few new services wrapped in a huge marketing blitz. The company, for example, will spend five to seven times more this year than last on marketing its BI wares.


    The IBM announcements center on DecisionEdge, which is an IBM service program that deals with customer relationship marketing, and Discovery, which includes product announcements and additional services. Discovery itself is an umbrella term that covers IBM's Visual Warehouse and Data Miner products.








    The only thing BI guarantees is the feeling that we're making the right decisions based on the data we have.





    It's safe to say that most companies have access to a large enough quantity of data to make reasonable business decisions. The data they have, however, may not be usable. Like trying to search for a particular phrase in a library of books, or a person in the phone book when all you have is a first name, the problem lies with the presentation of data--not the amount.


    BI tools and services help filter information. IBM's Intelligent Miner, in particular, does an excellent job of sifting through and categorizing data into meaningful information. But there are a lot of interesting BI implications. The best solutions are enormously expensive, more than $10 million (including hardware and setup) for a big site. They are also very vertical, targeting specific industries such as the insurance and medical fields.


    Can BI help you? For those industries, and particularly for the rest of us, the only thing BI guarantees is the feeling that we're making the right decisions based on the data we have. But there are other implications with BI. A kind of pecking order emerges as those who have access to data have all the power, regardless of whether they can make the right decision.


    Carry that forward a little bit and the companies that have the best access to coherent data, in turn, have the most power.


    That's just about where the real data mining business is. It's in the hands of the 500 most powerful companies in the country, those that can afford to spend half a million bucks on a departmentwide implementation.


    Whether those companies can do anything with data is another story. CBS has incredibly rich historical and real-time data (much of it provided by IBM), and it couldn't put on a good Olympics show.


    What about all the data that the United States is gathering on Iraq? Will it be put to good use? We shall see.



  • When do you think BI tools will empower the rest of us? John Taschek can be reached at john_taschek@zd.com.







  • Previous  3 Next   Top
    From: Alex Chelminsky achelminsky@kstream.com
    Subject: SPSS and ISL
    Date: Tue, 3 Mar 1998 08:44:10 -0600

    ISL and SPSS in Partnership To Provide the Complete
    Enterprise Data Mining Solution (Business Wire; 732 words; 03/03/98)

    KING OF PRUSSIA, Penn.--(BUSINESS WIRE)--March 3, 1998--
    ISL Decision Systems Inc., U.S. affiliate of leading data mining product
    supplier Integral Solutions Limited, Basingstoke, U.K., announced
    today the completion of an alliance with SPSS Inc., the leading
    supplier of desktop business analysis and data mining software. Under
    the agreement, the companies will develop an interface between ISL's
    award winning Clementine(R) data mining product and SPSS data mining
    and statistics product line, SPSS for Windows(TM)

    for details see
  • www.isl.com
  • and
  • www.spss.com


  • Previous  4 Next   Top
    From: 'Anand, Tej' TAnand@HITC.AtlantaGA.ncr.com
    Subject: Tej Anand is now Golden Books Family Entertainment CIO
    Date: Fri, 6 Mar 1998 09:00:29 -0500

    Dear colleagues - After approximately five glorious years at NCR Corporation
    I have decided to resign from NCR and join Golden Books Family Entertainment
    as their CIO. I will miss all my associates at NCR, but I am looking forward
    to my new role as a 'user' of technology. I have always believed that
    knowledge discovery should be an integral part of the way a company does
    business - it should be tightly woven into sales, marketing, manufacturing,
    distribution, new product creation and finance. In my new role I am hoping
    to be associated with a case study where this view of knowledge discovery is
    implemented. I am counting on help from all of you in making this happen. My
    new contact information is as follows:
    Address: Golden Books Family Entertainment, 888 Seventh Avenue, New York, NY
    10106-4100
    Phone: (212) 547-6702
    Fax: (212) 547-6779
    E-mail: tanand@goldenbooks.com.
    See you at KDD-98!
    Regards, -Tej Anand


    Previous  5 Next   Top
    From: Alex Chelminsky achelminsky@kstream.com
    Subject: Information Week: Data Mining at GM
    Date: Tue, 10 Mar 1998 08:08:31 -0600

    Information Week
    February 23, 1998, Issue: 670
    Section: Software


    GM Goes Data Mining -- Tests will lead to 'serious'
    investment

    Joy D. Russell

    General Motors Corp. is evaluating several data mining products
    for projects the company plans for this year and next, involving
    several GM divisions, including its GMAC loan division and its
    credit-card division.

    GM has experimented with data mining on a few scientific
    projects, but it is only in the past two years that the automaker
    has tried to use data mining in production work to solve
    problems like database marketing, using customer data and
    warranty information, says Ramasamy Uthurusamy, director of
    emerging technologies in GM's information systems and services
    division.

    'Some people think data mining is getting software and starting
    to run some programs, but it's not,' explains Uthurusamy. 'The
    biggest difficulty in implementing any data mining strategy is
    trying to extract clean and reliable data before you do the
    mining. We have spent a lot of money on that alone.'

    GM's first pilot, planned for rollout late this year, is the mining
    of warranty information. 'What we'd like to learn from warranty
    data is how to identify problems early enough, so we can go
    back stream and fix them,' says Uthurusamy. 'For example, if I
    can learn that a particular [car] part is going bad in a specific
    vehicle, I can go back to the supplier that provides the part, and
    avoid future warranty expenses.'

    Since the beginning of the year, Uthurusamy has been testing
    three data mining products:IBM's Business Discovery Solutions,
    which includes its Intelligent Miner product; SAS Institute's
    Enterprise Miner, slated to ship in April; and Silicon Graphics'
    MineSet.

    Uthurusamy says each product has strengths. 'If our business
    problem requires a good visualization tool, Silicon Graphics'
    MineSet has that strength,' he says. 'If I'm looking for
    associations between different variables, IBM's Intelligent Miner
    works well. And if I'm looking at statistical techniques, SAS's
    Enterprise Miner is useful.' GM has IBM DB2, Oracle, and
    SAS databases. 'We won't ever have a situation where we'll use
    one tool, but perhaps a combination of each.'

    All three big U.S. car makers are testing SAS's Enterprise Miner,
    particularly in segmentation and profiling, customer acquisition
    and retention, churn analysis, and fraud detection, says Mark
    Brown, SAS's program manager for data mining.

    Adds GM's Uthurusamy:'Data mining is very important to GM.
    We are still in exploratory stages. But we hope to seriously start
    investing [in data mining] once we show some results.'

    Copyright (c) 1998 CMP Media Inc.

    You can reach this article directly here:
    http://www.techweb.com/se/directlink.cgi?IWK19980223S0047


    Previous  6 Next   Top
    From: david_hatter@mcgraw-hill.com
    Date: Thu, 05 Mar 98 13:25:06 -0500
    Subject: Proposed book on Data Mining
    website: http://www.mcgraw-hill.co.uk

    ***************************************************************************
    ** Your views are requested on a proposed new publication in Data Mining **
    ***************************************************************************
    At McGraw-Hill we have a proposal from Sarab Anand of Ulster University on the
    subject which is being considering for publication. The proposal, which is
    summarised below, has been reviewed and has received praise for its technical
    and academic fidelity; we now need to assess the interest in the book among the
    informed community. What I would like to ask, therefore, is whether you
    would be interested in the book, for your own use or as a text for students. A
    brief e-note indicating your view, together with any observation which occurs to
    you would help me greatly. An indication of the extent to which the subject
    appears in advanced u/g and p/g courses would be particularly useful. In the
    event of there being support for its publication we would be pleased to make it
    available at a preferred price for members of this group.

    Thank you very much for your help. It is our view at McGraw-Hill that the book
    promises to be a significant addition to the literature and your response will
    assist us in our decision on whether to publish. Please address your response to
    me, dave_hatter@mcgraw-hill.com

    1: Introduction; Anand, Buchner, Hughes
    Overview of Data Mining technologies. What Data Mining is and why it is needed.
    PART I: Data Pre-Processing
    2: Dealing with Missing Data; Ken Totton, Gavin Meggs, Blaise Egan (BT)
    Most common attribute value to bayesian and statistical models.
    3: Data Dimensionality Reduction; Ron Kohavi(Stanford), McClean,Scotney (Ulster)
    Covers techniques to reduce the dimensionality of the data.
    4: Noise Modelling; Ray Hickey (Ulster)
    'How can a discovery algorithm cope with inaccurate data'
    PART II Discovery Methodologies; Machine Learning Based Techniques
    5: Rule Induction / Information Theory: Padhraic Smyth (U of California, Irvine)
    The use of Information Theoretic measures within rule discovery is studied.
    6: Conceptual Clustering; A Doug Talbert, Doug Fisher, Vandebilt U, Tennessee
    Discusses problems in present clustering techniques & presents novel solutions.
    7: Heuristic Techniques; V. Rayward-Smith (University of East Anglia)
    Techniques such as Simulated Annealing, Genetic Algorithms & hybrid techniques.
    8: Connectionism and Data Mining; Liu, Setiono (National U of Singapore)
    This chapter discusses techniques available for rule extraction.
    Uncertainty Based Techniques:
    9: Rough Set Analysis; Ivo Duntsch (Ulster), Gunther Gediga (Onsabruck, Germany)
    Basic concepts & two techniques for obtaining a logic of rough sets
    10: Bayesian Belief Networks and L-L Modelling; Shapcott, Bell, Liu (Ulster)
    Basic concepts of l-l models for two variables & their generalisation.
    Database Support for Data Mining:
    11: Database Support for Attribute Oriented Induction;J.Han (Simon Fraser U)
    Attribute Oriented Induction operations mapped onto database operations.
    12: Discovery in Distributed and Heterogeneous Databases;Bell,Anand,Hua (Ulster)
    Initial work on requirements for distributed database support for discovery.
    13: Distributed Statistical Databases; McClean, Scotney (Ulster)
    The structure of a micro/macro data model and relations is examined.
    PART III The Role of the Human:
    14: Using Background Knowledge; A. Tuzhilin (New York University)
    Covers the role of domain knowledge within Data Mining.
    PART IV Knowledge Post-Processing
    15: Knowledge Filtering; Friedrich Gebhardt (GMD Labs, Germany )
    Covers both aspects of interestingness discussing its different facets and
    providing a survey of measures used to address each of these facets. Covers both
    objective as well as subjective measures.
    16: Knowledge Validation; Ken Totton, Gavin Meggs, Blaise Egan BT Labs, England
    A number of different approaches to knowledge validation are reviewed.


    Previous  7 Next   Top
    Date: Fri, 6 Mar 98 22:31:55 EST
    From: michalsk@aic.gmu.edu (Ryszard S. Michalski)
    Subject: NEW BOOK: MACHINE LEARNING & DATA MINING

    New Book Announcement

    MACHINE LEARNING & DATA MINING
    Methods and Applications

    Edited by
    Ryszard S. Michalski, George Mason University, USA
    Ivan Bratko, University of Ljubljana, Slovenia
    Miroslav Kubat, University of South Western Louisiana, USA

    Published by John Wiley & Sons, Ltd., Chichester, UK
    January, 1998, 472pp, Cloth 0-471-97199-5

    This book is the first major text dedicated to issues at the intersection of
    machine learning and data mining. Written by a team of international experts,
    it presents an exciting contribution addressing the challenge of extracting
    knowledge from various kinds of data. It provides an introduction to basic
    methods and its coverage spans the analysis of numerical data, text, images
    and sound. Most impressively, this book describes applications across a wide
    spectrum of real world problems, in domains such as engineering, control,
    biology, medicine and music.

    The book is aimed primarily at practitioners working in disciplines outside
    computer science, offering Machine Learning as a successful alternative to
    the traditional approaches to extracting knowledge from data. It will
    also serve as a useful survey text for students and researchers.

    CONTENTS
    Preface
    PART I GENERAL TOPICS
    Ch.1: A Review of Machine Learning Methods
    Ch.2: Data Mining and Knowledge Discovery: A Review of Issues
    and a Multistrategy Approach
    Ch.3: Fielded Applications of Machine Learning
    Ch.4: Applications of Inductive Logic Programming

    PART II DESIGN AND ENGINEERING
    Ch.5 Application of Machine Learning in Finite Element Computation
    Ch.6 Application of Inductive Learning and Case-Bawed Reasoning for
    Troubleshooting Industrial Machines
    Ch.7 Empirical Assembly Sequence Planning: A Multistrategy Constructive
    Learning Approach
    Ch.8 Inductive Learning in Design: A Method and Case Study Concerning Desing
    of Antifriction Bearing Systems

    PART III DETECTION OF PATTERNS IN TEXTS, IMAGES and MUSIC
    Ch. 9 Finding Associations in Collections of Text
    Ch.10 Learning Patterns In Images
    Ch.11 Applications of Machine Learning to Music Research: Empirical
    Investigations into the Phenomenon of Musical Expression

    PART IV COMPUTER SYSTEMS and CONTROL SYSTEMS
    Ch.12 WebWatcher: A Learning Apprentice for the World Wide Web
    Ch.13 Biologically Inspired Defences Against Computer Viruses
    Ch.14 Behaviural Cloning of Control Skill
    Ch.15 Acquiring First-order Knowledge About Air Traffic Control

    PART V MEDICINE and BIOLOGY
    Ch.16 Application of Machine Learning to Medical Diagnosis
    Ch.17 Learning to Clarify Biomedical Signals
    Ch.18 Machine Learning Applications in Biological Classification of
    River Water Quality

    ORDERING INFORMATION

    PAID ORDERS: All Wiley books can be obtained through your local bookseller
    Books can also be ordered directly, depending on where you are in the world.
    For details, visit: http://www.wiley.com/ordering/

    Books can be ordered online at: http://catalog.wiley.com/

    INSPECTION COPIES: They are available to lecturers considering the book for
    adoption on their courses. In Europe, Middle East and Africa contact:
    Inspection Copies, Sales Support Dept., John Wiley & Sons Ltd., Baffins Lane,
    Chichester, W. Sussex. PO19 1UD. UK
    Tel.: +44-(0)1243-770-372 Fax: +44-(0)1243-770-571 E-mail: college@wiley.co.uk

    For details of how to order inspection copies in the USA, Latin American
    and the Caribbean, visit: http://www.wiley.com/ordering/books.html


    Previous  8 Next   Top
    Date: Wed, 11 Mar 1998 22:50:13 -0500
    From: Maria Zemankova mzemanko@nsf.gov
    Subject: Digital Libraries Initiative - Phase 2
    Website: http://www.nsf.gov/home/crssprgm/dli/start.htm

    Updated information is now available on the NSF Online
    Document System for the following document (nsf9863):

    Title: Digital Libraries Initiative - Phase 2
    Type: Program Announcements & Information
    Subtype: Computer/Information Sciences, Crosscutting Programs,
    Education, Social/Behavioral Sciences


    Information is available now about
  • East and West Coast

  • Public Briefings
    .

    It may be found at:

    http://www.nsf.gov/cgi-bin/getpub?nsf9863

    --
    NSF Custom News Service
    http://www.nsf.gov/home/cns/start.htm
    Please send questions and comments to webmaster@nsf.gov

    Previous  9 Next   Top
    Date: Mon, 09 Mar 1998 22:50:13 -0500
    From: Nahum Gershon gershon@mitre.org
    Subject: CALL FOR PAPERS: Journal of Intelligent Information Systems
    http://www.isse.gmu.edu/JIIS/

    Special Issue on INFORMATION VISUALIZATION
    http://www.isse.gmu.edu/JIIS/informat.html

    Guest Editors:
    Nahum Gershon gershon@mitre.org
    Stephen G. Eick eick@bell-labs.com

    PAPER SUBMISSION & PUBLICATION
    Deadline for Submission: April 15, 1998 (NEW)
    7 copies of the 20-25 page papers should be sent to:

    Nahum Gershon
    The MITRE Corp.
    1820 Dolley Madison Blvd.
    McLean, VA 22102, USA

    Final manuscripts due: June 10, 1998

    Please see Instructions for Authors in Special Issues:
    http://www.isse.gmu.edu/JIIS/
    Should you anticipate problems in delivering your final manuscript in JIIS
    macros, please notify the Guest Editors as soon as your receive the notice
    that your paper is accepted for publication in the special issue.

    Publication Date: Fall 1998


    Previous  10 Next   Top
    Date: Thu, 26 Feb 1998 17:20:52 +0000
    From: ROSS DONALD KING rdk@aber.ac.uk
    Subject: Data Mining Ph.D. Studentships

    Field: Data Mining, Bioinformatics and Biocomputing
    Place: University of Wales, Aberystwyth
    Wales, UK

    Ph.D. studentships are available in the area of data mining
    in the Bioinformaticsand Biocomputing research group of the
    Department of Computer Science,University of Wales, Aberystwyth.
    Applicants should have a first or upper second class honours degree,
    or equivalent qualifications, in a relevant subject.

    The research group is concerned with developing computing and
    artificial intelligence techniques for application to important
    biological problems. We aim to do innovative research in both
    computer and biological science. An essential component of our success
    in this multidisciplinary field is our close collaboration with the
    biotechnology and pharmaceutical industries, and with others in academia.

    Our academic collaborators include Prof. Douglas Kell's Quantitative
    Biology and Analytical Biotechnology Group in the Institute of
    Biological Sciences (IBS) here at Aberystwyth and the ILP Group at the
    University of Oxford. Industrial collaborators include major
    pharmaceutical companies and manufacturers of analytical instrumentation

    Our main interests are machine learning and chemometrics for data
    mining and data interpretation. Techniques include:

    Inductive Logic Programming (ILP), Model Based Reasoning,
    Evolutionary computing, Artificial neural networks, Multivariate statistics.

    Applications of our work include:
    Drug Design, Protein Secondary Structure Prediction,
    Functional Genomics,
    Spectral interpretation for process monitoring, titre improvement,
    and organism identification.

    More information can be obtained from
    Ross D. King or Jem Rowland

    Department of Computer Science,
    University of Wales, Penglais, Aberystwyth, Ceredigion, SY23 3DB,
    Wales, UK
    Tel: +44 1970 622420 Fax: +44 1970 622455
    Email: rdk@aber.ac.uk jjr@aber.ac.uk

    or from the URL: http://www.aber.ac.uk/~dcswww/Research/bio/


    Previous  11 Next   Top
    Date: Tue, 3 Mar 1998 12:51:07 -0800 (PST)
    From: Hal Duncan hal@scotland.arc.nasa.gov
    Subject: JOBS AVAILABLE: RESEARCH PROGRAMMERS, NASA AMES

    Two jobs available at NASA Ames Research Center for
    Machine Learning / Data Mining Research Programmers

    The Data Understanding Group at NASA Ames Research Center is undertaking
    a project to provide advanced data mining and machine learning tools for
    NASA's onboard spacecraft scientific experiments. The near-term goals
    of the project are to provide an inference system for surface topography
    and mineralogy, from domains including satellite imaging systems, airborne
    imaging systems, and ground-based (lander and rover) imaging systems. The
    long-term goals are to provide tools to build on the surface topography
    and mineralogy mapping to yield automatic feature inference, detect regions
    of interest, perform goal and task oriented recognition, and offer science
    goal advice.

    Caelum Research Corporation has two contract positions open at NASA Ames
    to join the Data Understanding team designing and coding the surface
    inference system (and other inference tools as they evolve). This is the
    core project of a larger effort to provide spacecraft and landers with
    autonomous science understanding. The positions involve elements of design
    and development, interfacing with research scientists on a frequent basis,
    less frequent discussions with domain experts, and building and testing
    within the context of the overall architecture. The architecture of the
    system involves several advanced technologies, which include pushing the
    frontier on automatic model inference, Bayesian methodologies, rendering,
    clustering, and classification. Opportunities to participate in intense
    collaborative research with researchers within the Data Understanding group
    abound. For energetic individuals interested in challenging programming
    and desiring challenging frontier experience with advanced data mining and
    data understanding methods, this is the opportunity of a lifetime.

    Candidates for this position must hold a degree in Computer Science,
    Physics, Electrical Engineering or a related area, and must possess
    strong programming skills in C and C++, as well as have experience with
    the UNIX environment. Strong social skills, a desire to be part of a
    team, and high energy are key requirements. Familiarity with statistical
    methods, probability theory, pattern recognition, and/or image processing
    are a plus.

    Caelum Research Corporation is a contractor at NASA Ames Research Center,
    which is located near Mountain View in the south San Francisco Bay area,
    in the heart of the Silicon Valley. The positions offer a competitive
    compensation package, excellent benefits, the opportunity to join a
    well-motivated, hard-working team, and the chance to directly impact the
    future of the U.S. Space and Aeronautics programs.

    Only U.S. citizens or green card holders are eligible for these positions.

    Applicants should send a resume to:

    Hal Duncan
    ATTN: MARS-INFER
    MS 269-2, NASA Ames Research Center
    Moffett Field, CA 94035-1000
    email: hduncan@mail.arc.nasa.gov

    Email is preferred (plaintext, Postscript, or Macintosh MS Word), with the
    subject line 'ATTN: MARS-INFER'. Please be prepared to supply three letters
    of recommendation from recent employers or professors.


    Previous  12 Next   Top
    From: Rob Gerritsen rob@xore.com
    Subject: Exclusive Ored Data Mining Seminar
    Date: Tue, 24 Feb 1998 09:16:47 -0500
    Website: http://www.xore.com

    Exclusive Ore Inc. announces a one-day course on data mining entitled
    'Turning Data into $$$,' to be held on April 22 in Conshohocken, PA
    (near Philadelphia). The course will cover knowledge discovery in
    general, discuss how data mining is used to build a model, examine
    several modeling techniques (including selected demonstrations),
    review features of the leading products on the market today, and
    conclude with a discussion of how to plan and execute a successful
    data mining project. For more information, see
  • www.xore.com.



  • Previous  13 Next   Top
    Date: Mon, 02 Mar 1998 12:16:07 +0000
    From: Alex H B Duffy alex@cad.strath.ac.uk
    Organization: CAD Centre, University of Strathclyde
    Subject: Machine Learning in Design

    Call for Papers

    A workshop on Machine Learning in Design (MLinD) is being held on the
    prior to the 5th International Conference on Artificial Intelligence in Design
    (AID'98) in Portugal this July.

    The workshop is intended to provide a forum for provocative discussion
    related to the application and evolution of machine learning techniques
    in design.

    The purpose of the workshop is to build upon the results of previous
    work by exploring the development of a more fundamental foundation
    for MLinD research. In particular the workshop will endeavour to provide
    a forum for new ideas or criticisms of previous endeavours. The objective
    is to evolve a core understanding of the issues and key areas for future
    research and to stimulate synergy in the Machine Learning in Design
    research community.

    Position papers of not more than 6 pages are invited to be submitted by
    the 29 May.

    Numbers are restricted to around 20-30 participants. Admission, as
    determined by a selected panel, will be based upon the expediency of
    the submitted position papers and limited to attendees of the AI in
    Design conference.

    For further information see:

    http://www.cad.strath.ac.uk/~alex/AID/AID98/AID98-MLinD.html
    _____________________________________________________________________
    Dr A H B Duffy Tel: +44 141 548 3134
    CAD Centre Fax: +44 141 552 3148
    University of Strathclyde E-mail: alex@cad.strath.ac.uk
    75 Montrose Street URL: http://www.cad.strath.ac.uk

    Glasgow G1 1XJ, UK.


    Previous  14 Next   Top
    Date: Thu, 05 Mar 1998 10:11:18 +0100
    From: Riccardo Bellazzi ric@aim.unipv.it
    Subject: IDAMAP-98: a reminder
    IDAMAP-98
    Inteligent Data Analysis in Medicine and Pharmacology
    A Workshop at the 13th European Conference on Artificial Intelligence

    Call for Papers: A reminder
    Paper submission deadline: April 15, 1998

    IDAMAP-98 is a one day ECAI-98 workshop that will be held in Brighton,
    UK, on Tuesday, August 25, 1998 prior to the start of the main ECAI
    conference. The topics of the workshop are computational methods for
    data analysis able to exploit the available knowledge to narrow the
    gap between data gathering and data comprehension, as well as their
    applications in medicine and pharmacology.

    The scientific program will consist of presentations of accepted
    papers and panel discussions. We invite you to submitt a paper in a
    zipped or g-zipped postscript or rtf format to the e-mail address
    idamap98@aim.unipv.it. The preferred length of papers is of about 5000
    words (10 pages).

    Accepted papers will be published in the IDAMAP-98 working
    notes. Based on selected workshop papers, we plan to edit a special
    issue of the Applied Artificial Intelligence Journal.

    For additional information, see http://aim.unipv.it/~ric/idamap98
    ==================================================
    Contact Person for IDAMAP 98: Riccardo Bellazzi, PhD
    Dipartimento di Informatica e Sistemistica
    Universita' di Pavia, via Ferrata 1, 27100 Pavia, Italy
    tel: 39-382-505-511, fax:39-382-505-373
    e-mail: ric@aim.unipv.it



    Previous  15 Next   Top