Jesse Davis



Professor

Address:
Dept. of Computer Science
Katholieke Universiteit Leuven
Celestijnenlaan 200A
3001 Heverlee
Belgium

Telephone:
Fax: +32 16 32 79 96
Email: first name + dot + last name at cs dot kuleuven dot be
Office: 1.06

About Me

I joined K.U. Leuven in October 2010. I am a member of the Machine Learning group within the Declarative Languages and Artificial Intelligence Lab (DTAI).

I also work on sports analytics.

I did a post-doc with Pedro Domingos at the University of Washington. I worked on Markov logic networks, which are publicly available as the Alchemy system. I am also involved with our recent MURI award entitled A Unified Approach to Abductive Inference. I did my Ph.D at the University of Wisconsin-Madison under the supervision of David Page.

News

I'm co-guest editor of the Machine Learning Journal Special Issue on Inductive Logic Programming. Please consider submitting! See the call for papers for details. Deadline: December 14th, 2014.

Vito, WZC Witte Meren, DTAI and Group T have received the biannual Janssen open innovation award van de Kempense Innovatieraad (KIR) for their Cycling Through the Past for the Elderly project. The DTAI team working on this project includes Wannes Meert, Jeroen Mordijck, Tim Op Beeck and myself. There was also an article about the project in the De Standaar and De Campuskrant.

We conducted an analysis of the World Cup group stages where we evaluate the performance of the various teams and regions.

We have released a performance analysis on the 2013-2014 playoffs for the Belgian Pro Soccer League. The full press release is available from the KU Leuven press website.

We have released a performance analysis of the 2013-2014 season of the Ethias League, which is the Belgian professor basketball league. The full press release is available from the KU Leuven press website.

We have released a performance analysis of the 2013-2014 season of the Belgian Pro Soccer League. The full press release is available from the KU Leuven press website. The story has appeared multiple papers, including De Morgen and De Standaard. For information, see our sports analytics website.

I will be program co-chair for the 24th International Conference on Inductive Logic Programming.

We organized a workshop on sports analytics at ECML/PKDD 2013.

Education

  • Ph.D in Computer Sciences from the University of Wisconsin-Madison. (August 2007)
  • M.S. in Computer Sciences from the University of Wisconsin-Madison. (May 2005)
  • B.A. in Computer Science from Williams College. (June 2002)

    Current PhD Students

  • Jessa Bekker
  • Marc Mertens (joint with Bart Vanrumste)
  • Tim Op De Beeck
  • Irma Ravkic
  • Jan Van Haaren
  • Aaron Verachtert

    Former Post-docs

  • Nima Taghipour (Joint with Hendrik Blockeel)
  • Martin Znidarsic (Joint with Jan Ramon)

    Former PhD Students

  • Nima Taghipour, graduated March 2013 (Primary advisor: Hendrik Blockeel)

    Software

    I have written a c++ package for learning the structure of a Markov network. It can be found here.

    Jan Van Haaren and I have another system, called GSSL, for learning the structure of a Markov network.

    The source code for our TODTLER system for transfer learning is also publicly available. See our AAAI 2015 paper for more details.

    Mark Goadrich and I have written a java package for generating ROC and Precision Recall curves. It can also calculate the area under the curve. The jar file is available here. For more information about ROC and PR curves, see our paper at ICML 2006.

    Selected Publications

    Journals

    Refereed Conferences

    Book Chapters

    Refereed Workshops

    Teaching

    I teach a classes on Programming for Big Data and Data Mining as a part of the master in artificial intelligence program.

    Seminars

    When I was at the Univeristy of Washington, I ran the machine learning reading group.

    In the spring of 2008, I ran a seminar on Biomedical Applications of Artificial Intelligence.

    Professional Service