2004 IEEE Workshop on
                 Machine Learning for Signal Processing

         Formerly called Neural Networks for Signal Processing

               Sep. 29 - Oct. 1st, 2004, SC#o LuC-s, Brazil
            Sponsored by the IEEE Signal Processing Society

                            Call for Papers

The fourteenth of a series of IEEE workshops on Machine Learning for
Signal Processing will be held in SC#o LuC-s
(http://www.turismo.ma.gov.br/en/), Brazil.  SC#o LuC-s is located just in
between Amazonia and the Northeast coast, and is a World Heritage
island. It is the only capital city in Brazil founded by the French. It
has a wonderful Portuguese Historical Center, along with exquisite local
seafood, and is close to one of the most beautiful deserts in the world:
LenC'ois Maranhenses, where pristine water lays lazily distributed among
beautiful dunes.

This is a continuation of a series of workshops named Neural Networks
for Signal Processing (NNSP). The technical committee decided to change
the name to better reflect the community scope, and the rapid changes in
the field.

The workshop will feature keynote addresses, technical presentations,
special sessions and tutorials that will be included in the
registration. Papers are solicited for, but not limited to, the
following areas:

Algorithms and Architectures: Artificial neural networks, kernel
methods, committee models, Gaussian processes, independent component
analysis, advanced (adaptive, nonlinear) signal processing, (hidden)
Markov models, Bayesian modeling, parameter estimation, generalization,
optimization, design algorithms.

Applications: Speech processing, image processing (computer vision,
OCR), multimodal interactions, multi-channel processing, intelligent
multimedia and web processing, robotics, sonar and radar, bio-medical
engineering, financial analysis, time series prediction, blind source
separation, data fusion, data mining, adaptive filtering,
communications, sensors, system identification, and other signal
processing and pattern recognition applications.

Implementations: Parallel and distributed implementation, hardware
design, and other general implementation technologies.

MLSP'2004 webpage:      http://isp.imm.dtu.dk/mlsp2004

Paper Submission
Procedure Prospective authors are invited to submit a full paper of up
to ten pages using the electronic submission procedure described at the
workshop homepage. Accepted papers will be published in a bound volume
by IEEE after the workshop and a CDROM volume will be distributed at the
workshop.

Schedule
  Submission of full paper:
    April 15, 2004

  Notification of acceptance:
    May 15, 2004

  Camera-ready paper and author registration:
    June 1, 2004

  Advance registration before:
    July 31, 2004


General Chairs
  Allan Kardec BARROS
    Universidade Federal do MaranhC#o

  JosC) PRINCIPE
    University of Florida at Gainesville

Program Chairs
  Jan LARSEN
    Technical University of Denmark

  TC