| |
The  Project
Basic Research ESPRIT project Number 6891:
Enhanced Learning for Evolutive Neural Architectures
Framework
 |
Summary
ELENA Project concerns learning in Neural Networks for classification tasks, both by
adding or removing neurons in the network, and by synaptic adaptation. Project includes
theoretical work on these algorithms, simulations and benchmarks, especially on realistic
industrial data. Hardware implementation, especially VLSI option, is the last objective.
|
|
Aim
Neural network applications are mainly devoted to classification. Most of the usual neural
algorithms are unusable for practical applications: for instance, the architecture cannot
easily grow, and it is difficult to learn new classes. The Project deals with neural
algorithms with evolutionary architectures, and proposes a consistent set of preprocessing
and classification algorithms, looking at their hardware implementation.
|
|
Potentiality
The results of ELENA will provide tractable methods to carry out realistic problems in
classification. The tests and benchmarcs to be performed constitute convincing
applications of neural network efficacity.
|
[Top]
The three main axes of Elena
|
Axis A: Theory
Partners:
Thomson-Sintra ASM (coordinator), EERIE, INPG, UCL, UPC, EPFL.
Objectives:
Axis A contains three tasks,
Al: Architecture modification critera,
A2: Confusion prediction,
A3: Relations with classical methods.
|
|
Axis B: Simulation and Benchmarks
Partners:
INPG (coordinator), EPFL, EERIE, UCL, UPC, Thomson-Sintra ASM
Objectives:
The Axis B is splitted in 4 Tasks concerning
B1: Databases,
B2: Unified graphic environment,
B3: Software simulators,
B4: Benchmarking.
|
|
Axis C: Hardware Implementation
Partners:
UCL (coordinator), UPC, EPFL, EERIE, INPG
Objectives:
The Axis C is splitted in 3 Tasks concerning
Cl: Hardware constraints,
C2: Architecture specification,
C3: Design of building blocks.
|
[Top]
Available stuff
The partners of the Elena project are pleased to announce you the availability of
several databases related to classification together with two technical reports.
The set of databases available is to be used for tests and benchmarks of
machine-learning classification algorithms. The databases are splitted into two parts:
ARTIFICIALly generated databases, mainly used for preliminary tests, and REAL ones, used
for objective benchmarks and comparisons of methods.
The choice of the databases has been guided by various parameters, such as availability
of published results concerning conventional classification algorithms, size of the
database, number of attributes, number of classes, overlapping between classes and
non-linearities of the borders,... Results of PCA and DFA preprocessing of the REAL
databases are also included, together with several measures useful for the databases
characterization (statistics, fractal dimension, dispersion,...).
All these databases and their preprocessing are available together with a postcript
technical report describing in details the different databases (Databases.ps.Z
- 45 pages - 777781 bytes) and a report related to the comparative benchmarking studies of
various algorithms (Benchmarks.ps.Z
- 113 pages - 1927571 bytes) well-known by the Statistical and Neural Network communities
(MLP, RCE, LVQ, k_NN, GQC) or developped in the framework of the Elena project (IRVQ,
PLS).
A LaTeX bibfile containing more than 90 entries corresponding to the Elena partners
bibliography related to the project is also available (Elena.bib)
in the same directory.
All files are available by anonymous ftp from the following directory:
ftp://ftp.dice.ucl.ac.be/pub/neural-nets/ELENA/databases
The databases are splitted into two parts: the 'ARTIFICIAL' ones, being generated in
order to obtain some defined characteristics, and for which the theoretical Bayes error
can be computed, and the 'REAL' ones, collected in existing real-world applications.
The ARTIFICIAL
databases ('Gaussian', 'Clouds' and 'Concentric') were generated according to the
following requirements:
| heavy intersection of the class distributions, |
| high degree of nonlinearity of the class boundaries, |
| various dimensions of the vectors, |
| already published results on these databases. |
They are restricted to two-class problems, since we believe it yield answers to the
most essential questions. The ARTIFICIAL databases are mainly used for rapid test purposes
on newly developed algorithms.
The REAL
databases ('Satimage', 'Texture', 'Iris' and 'Phoneme') were selected according to the
following requirements:
| classical databases in the field of classification (Iris), |
| already published results on these databases (Phoneme, from the ROARS ESPRIT project and
'Satimage' from the STATLOG ESPRIT project), |
| various dimensions of the vectors, |
| sufficient number of vectors (to avoid the ``empty space phenomenon''). |
| the 'Texture' database, generated at INPG for the Elena project is interesting for its
high number of classes (11). |
[Top]
|
