NEURAL, SYMBOLIC, AND REINFORCEMENT METHODS FOR SEQUENCE LEARNING
to be held during IJCAI'99
Stockholm, Sweden, 31 July - 6 August, 1999
Sequence learning is an important component of learning in many task
domains: inference, planning, reasoning, robotics, natural language
processing, speech recognition, control, time series prediction,
financial engineering, DNA sequencing, etc. There are many different
approaches towards sequence learning, resulting from different
perspectives taken in different task domains. These approaches deal
with somewhat differently formulated sequential learning problems (for
example, some with actions and some without).
Sequence learning is a difficult task, and more powerful algorithms
are needed in all of these domains. The right approach is to better
understand the state of the art in different disciplines related to
this topic first. Therefore, there seems to be a need to compare,
contrast, and combine different techniques, approaches, and paradigms,
to develop more powerful algorithms. These techniques and algorithms
include recurrent neural networks, hidden Markov models, dynamic
programming (reinforcement learning), graph theoretical models,
evolutionary computational models, AI planning models, rule-based models, etc.
We need a gathering that includes researchers from all of these
orientations and disciplines, beyond narrowly focused topics such as
reinforcement learning or neural networks for sequential processing.
The following questions and issues will be addressed:
1. underlying similarity and difference of different models
1.1 problem formulation (ontological issues)
1.2 mathematical comparisons
1.3 task appropriateness
1.4 performance analysis and bounds
2. new and old model capabilities and limitations
2.1 theory
2.2 implementation
2.3 performance
2.4 empirical comparisons in various domains
3. hybrid models: approaches, theories and applications
3.1 foundations for synthesis or hybridization
3.2 necessity, advantages, problems, and issues
4. successful sequence learning applications and future extensions
4.1 examples of successful applications
4.2 generalization and transfer of successful applications
4.2 what is needed for enhancing performance
We will have invited speakers, panels, and regular submitted
paper presentations, and above all, extensive interactions and
discussions among participants.
1. We welcome submissions from all disciplines related to sequence
learning, including: AI researchers, cognitive scientists, control
engineers, computer scientists, neural network researchers, and
mathematicians, in the areas of recurrent neural networks, hidden
Markov models, dynamic programming (reinforcement learning), graph
theoretical models, evolutionary computational models, AI planning
models, rule-based models, etc.
2. To present a talk at the workshop, please submit (to one of the workshop
chairs) a short paper (between 2 and 7 pages), in the IJCAI paper format.
It must describe work and stating opinions relative to the above issues.
3. To participate in the workshop, submit a one-page description of interest
to one of the workshop chairs.
4. All submission should be through EMAIL, with plain Postscript
files.
5. time table:
February 15, 1999 Deadline for paper submission
March 15, 1999 Notification of acceptance
April 1, 1999 Camera ready copy
To encourage discussions, accepted contributions and discussion topics will
be published on the world wide web before the workshop. As a consequence,
the content of all the talks will be known beforehand, so that
presentations and discussions can focus on the technical questions. A web
discussion forum will also be provided for the attendees. Relevant parts
of these discussions will be briefly summarized beforehand
by session moderators as a starting point for the discussion sessions.
Hardcopy ``Working Notes" will be available at the workshop.
We are also considering publishing an edited book after the workshop
with a major publisher.
Dr. C. Lee Giles (co-chair)
NEC Research Institute
4 Independence Way
Princeton, NJ 08540, USA
Phone: 609-951-2642
Email: giles@research.nj.nec.com
http://www.neci.nj.nec.com/homepages/giles.html
Professor Ron Sun (co-chair)
Department of Computer Science
The University of Alabama
Tuscaloosa, AL 35487
Phone: 609-951-2781
Email: rsun@cs.ua.edu
http://cs.ua.edu/~rsun/
Committee members:
Jack Gelfand, Princeton Univeristy
Lee Giles, NEC Research Institute
Marco Gori, U. of Florence
Ron Sun, U of Alabama/NEC RI
Gerry Tesauro, IBM
Invited speakers:
Marco Gori, U. of Florence
Kevin Lang, NEC
Narajan, Cambridge Univeristy
Juergen Schmidhuber, IDSIA
Alexandro Sperdutti, U. of Pisa
Manuela Veloso, CMU