ENTNETS
Project EntNets - Entropic neural networks for the analysis of medical data
POSC/EIA/56918/2004, financed by FCT, POSC and FEDER.
Start date: 2005-06-01
End date: 2008-11-30
Financing: 77.000 €
Host Institution: University of Beira Interior (UBI)
Participating Institution: INEB - Instituto Nacional de Engenharia Biomédica
Goal
The goal of the project is the development of new neural networks using entropy as a cost function and their application to the analysis of medical data.Team
- Luís Filipe Barbosa de Almeida Alexandre (project coordinator)
- Carlos Alexandre da Silva Felgueiras
- Alexandra Alves Oliveira
- Joaquim Pontes Marques Sá
- Jorge Manuel Fernandes dos Santos
- Fernando Augusto Carneiro Sereno
- Luis Miguel Almeida da Silva
Most of the team members are researchers at the Neural Network Interest Group (NNIG).
Organized events
The Neural Network Summer Schools of 2005, 2006 and 2008 had the support of ENTNETS.The ICANN 2007 also had the support of ENTNETS.
Publications
The following is the list of publications that originated from ENTNETS.Ph.D. Thesis
J. Santos. Data Classification with Neural Networks and Entropic Criteria. PhD thesis, University of Porto, Portugal, 2007.
L.M. Silva. Neural Networks with Error-Density Risk Functionals for Data Classification. PhD thesis, University of Porto, Portugal, 2008.
Books
J. Marques de Sá, L.A. Alexandre, W. Duch, and D. Mandic, editors. Artificial Neural Networks -- ICANN 2007, Proceedings, Part I, Porto, Portugal, September 2007. Springer LNCS 4669.
J. Marques de Sá, L.A. Alexandre, W. Duch, and D. Mandic, editors. Artificial Neural Networks -- ICANN 2007, Proceedings, Part II, Porto, Portugal, September 2007. Springer LNCS 4668.
International Journals
J. Santos, J. Marques Sá, and L.A. Alexandre.
LEGClust - - A Clustering Algorithm Based on Layered Entropic Subgraphs.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(1):62--75, January 2008.L.M. Silva, C.A. Felgueiras, L.A. Alexandre, and J. Marques de Sá.
Error entropy in classification problems: A univariate data analysis.
Neural Computation, 18(9):2036--2061, September 2006.L.M. Silva, J.P. Marques de Sá, and L.A. Alexandre.
Data classification with multilayer perceptrons using a generalized error function.
Neural Networks, 21(9):1302--1310, November 2008.
International Conferences
M.J. Embrechts, L.A. Alexandre, J. Linton.
Reservoir computing for static pattern recognition.
accepted for the 17th European Symposium on Artificial Neural Networks - ESANN 2009, Bruges, Belgium, April 2009.L.A. Alexandre.
Maximizing the zero-error density for RTRL.
In 8th IEEE International Symposium on Signal Processing and Information Technology - ISSPIT 2008, Sarajevo, Bosnia and Herzegovina, December 2008. IEEE Press.L.A. Alexandre and J. Marques de Sá.
Error entropy minimization for LSTM training.
In 16th International Conference on Artificial Neural Networks - ICANN 2006, volume LNCS 4131 - part I, pages 244--253, Athens, Greece, September 2006. Springer.J. Santos, L.A. Alexandre, and J. Marques Sá.
Modular neural network task decomposition via entropic clustering.
In 6th International Conference on Intelligent Systems Design and Applications - ISDA 2006, volume 1, pages 62--67, Jinan, China, October 2006. IEEE Computer Society Press.J. Santos, J. Marques de Sá, and L.A. Alexandre.
Batch-sequential algorithm for neural networks trained with entropic criteria.
In 15th International Conference on Artificial Neural Networks- ICANN 2005, volume LNCS 3697, pages 91--96, Warsaw, Poland, September 2005. Springer.J. Santos, J. Marques de Sá, and L.A. Alexandre.
Neural networks trained with the EEM Algorithm: Tuning the Smoothing Parameter
In 6th WSEAS Int. Conference on Neural Networks, volume 4, pages 295--300, Lisbon, Portugal, June 2005.L.M. Silva, L.A. Alexandre, and J. Marques de Sá.
Neural network classification: Maximizing zero-error density.
In Third International Conference on Advances in Pattern Recognition - ICAPR 2005, volume LNCS 3686, pages 127--135, Bath, United Kingdom, August 2005. Springer.L.M. Silva, L.A. Alexandre, and J. Marques de Sá.
New developments of the Z-EDM algorithm.
In 6th International Conference on Intelligent Systems Design and Applications - ISDA 2006, volume 1, pages 1067--1072, Jinan, China, October 2006. IEEE Computer Society Press.L.M. Silva, M. Embrechts, J. Santos, and J. Marques de Sá.
The influence of the risk functional in data classification with MLPs.
In 18th International Conference on Artificial Neural Networks - ICANN 2008, volume LNCS 5163, pages 185--194, Praha, Check Republic, September 2008. Springer.L.M. Silva, J. Marques de Sá, and L.A. Alexandre.
Neural network classification using Shannon's Entropy.
In 13th European Symposium on Artificial Neural Networks - ESANN 2005, pages 217--222, Bruges, Belgium, 2005.
National Conferences
J. Santos.
Matriz de dissemelhança entrópica para classificação não supervisionada.
In Actas das XV Jornadas de Classificação e Análise de Dados -- JOCLAD2008, Porto, Portugal, Março 2008.
Technical Reports
J. Santos and J. P. Marques de Sá.
Human clustering on bi-dimensional data: An assessment.
Technical Report 2005-1, INEB-PSI, FEUP/DEEC, Porto, Portugal, 2005.A. Oliveira and J. P. Marques de Sá.
Neural network software tool development: exploring programming language options.
Technical Report 2006-1, INEB-PSI, FEUP/DEEC, Porto, Portugal, 2006.A. Oliveira and J. P. Marques de Sá.
Neural network software tool development in C#.
Technical Report 2006-2, INEB-PSI, FEUP/DEEC, Porto, Portugal, 2006.A. Oliveira and J. P. Marques de Sá.
Ferramenta computacional para implementação de redes neuronais - a primeira versão.
Technical Report 2007-1, INEB-PSI, FEUP/DEEC, Porto, Portugal, 2007.A. Oliveira and J. P. Marques de Sá.
Ferramenta computacional para implementação de redes neuronais - optimização das capacidades gráficas.
Technical Report 2007-2, INEB-PSI, FEUP/DEEC, Porto, Portugal, 2007.A. Oliveira and J. P. Marques de Sá.
Optimização da aplicação NNIG-Nets MLP e desenvolvimento da aplicação NNIG-Nets RBF
Technical Report 2008-1, INEB-PSI, FEUP/DEEC, Porto, Portugal, 2008.L.A. Alexandre.
A Solve-the-Equation Approach for Unidimensional Data Kernel Bandwidth Selection. Technical Report ISBN 978-989-654-005-0, DI-UBI, Covilhã, Portugal, 2008.
Webpage created and maintained by L. Alexandre