
Advanced School and Workshop on Soft Computing and Complex Systems
Program
Broad structure
The workshop will be organised around three main activities: lectures,
given by well known international experts, teamwork by the attendees,
to a solve particular problem proposed by the lecturers and, finally,
short presentations by the students about their own work and
interests.
Advanced School and Workshop on Soft
Computing and Complex Systems 
Coimbra, June 2327, 2003 

Schedule  Monday  Tuesday  Wednesday  Thursday  Friday 
8:30  9:00  Reception     
9:00  10:30 
Opening G. Dorffner Neural Computation DM 2.4 
R. Babuska Intelligent Control
DM 2.4 
J. Schmidhubber Recurrent Neural Networks
DM 2.4 
Team Work G. Dorffnner  DEI 
Team Work C. Fonseca  DEI 
10:30  11:00  Coffee break  Coffee break  Coffee break  Coffee break
 Coffee break 
11:00  12:30  R. Babuska NeuroFuzzy
Modelling DM 2.4 
J. Schmidhubber Universal Learning Algorithms
DM 2.4 
Teams Formation 
Team Work G. Dorffnner  DEI 
Team Work C. Fonseca  DEI 
12:30  14:00  Lunch  Lunch  Lunch  Lunch  Lunch 
14h00  15h30 
C. Fonseca MultiCriteria Genetic Optimisation DM 2.4 
Short Paper1 Short Paper2 Short Paper3 Short Paper4  Visit to the 
Team Work R. Babuska  DEI 
Team Work J. Félix Costa  DEI 
15:30  16:00  Coffee break  Coffee break  University
 Coffee break  Coffee break 
16:00  17:30 
J. Félix Costa Analog
Computation DM 2.4 
Short Paper5 Short Paper6 Short Paper7 Short Paper8 Short Paper9  
Team Work R. Babuska  DEI 
Team Work J. Félix Costa  DEI Closing

20:30     School Dinner   

DM  Departamento de Matemática (Department of
Mathematics) 
DEI  Departamento de Eng. Informático
(Departament of Informatics Engineering) 
SP1Piero Baraldi; SP2Rafaelle
Giordano; SP3José Ramos; SP4Luís Mujica; SP5Peter Posík 
SP6Helder Pinho; SP7Gonçalo
Silva; SP8André Ribeiro; SP9Amândio Marques

Each Lecture will last for one and a half hour. There will be a small
break between the lectures. Each team will have a lecturer assigned
to it to provide some help if needed. The results of each group will
be in the form of a written document, that will be the possible basis
for a paper to be submitted to an international conference.
 Lecture 1A:
 Neural Computation and
Applications in Time Series and Signal Processing.
 Speaker: Georg Dorffner
 Synopsis: The main architectures for neural computation will
be reviewed. The particular architectures for time series
prediction and signal processing will be studied.
 Lecture 2A:
 Analog
Computation
 Speaker: Félix Costa
 Synopsis: There will be short introduction to the new
promising area of analog computation. Some mathematical results,
about the power of this approach, will be presented as well as the
implications for the theory of computation.
 Lecture 1B:
 NeuroFuzzy Modeling
 Speaker: R. Babuska
 Synopsis: Clustering in its several forms will be studied for
structure learning from data in fuzzy systems. Parameter
optimisation through neural networks, composing neurofuzzy systems
will be reviewed and experimented.
 Lecture 2B:
 Intelligent Control
 Speaker: R. Babuska.
 Synopsis: The main recently developed techniques for advanced
Intelligent Control will be studied and experimented. Online
learning techniques, the problems of dimensionality, will be
discussed.
 Lecture 1C:
 Multicriteria Genetic Optimisation
 Speaker: Carlos Fonseca
 Synopsis: Genetic optimisation will be reviewed in its general
formulation. The particular case of multicriteria will then be
developed and discussed.
 Lecture 2C:
 Speaker: Juergen Schimdhuber
 Universal learning algorithms based on the theory of universal
induction and Kolmogorov complexity, with applications:

 Recurrent Neural Networks

RNNs are
artificial neural networks with adaptive feedback connections.
From training examples they can learn to map input sequences to
output sequences. They can implement almost arbitrary sequential
behavior. RNNs are biologically more plausible and
computationally more powerful than other adaptive models such as
Hidden Markov Models (no continuous internal states),
feedforward networks and Support Vector Machines (no internal
states at all)
