EDUCATION

 

Oct/95-Sep/99 Ph.D. in Electrical Engineering

Imperial College of Science, Technology and Medicine, London, UK

(Supervisor: Professor Igor Aleksander)

Title: Computability and Learnability in Sequential Weightless Neural

Networks

Sponsor: Brazilian Federal Agency for Post-Graduate Education (CAPES)

 

Mar/92-May/95 M.Sc. in Computer Science

Universidade Federal de Pernambuco, Recife-PE, Brazil

(Supervisor: Professor Teresa Ludermir)

Title: Computational Complexity of Learning in Weightless Neural Networks

Sponsor: Brazilian Research Council (CNPq)

Mar/88-Dec/91 B.Sc. in Computer Science

Universidade Federal do Rio Grande do Norte, Natal-RN, Brazil

 

WORK EXPERIENCE

 

Nov/10-current Visiting Professor

Centre of Informatics, Universidade Federal de Pernambuco (UFPE),

Recife-PE, Brazil

 

Sep/03-Oct/10 Associate Professor

Department of Informatics and Applied Mathematics, Universidade

Federal do Rio Grande do Norte (UFRN), Natal-RN, Brazil

Teaching: Artificial Intelligence, Machine Learning and Bioinformatics

courses for undergraduate and graduate students (Computer Science).

Administration: Deputy course director (Post-Graduation in Computer

Science) from Aug/08 – Jul/10; Deputy course director (B.Sc. in Computer Engineering)

from Sept/04 - Aug/06.

 

Oct/06-Sep/07 Visiting Researcher (Sabbatical leave from UFRN)

Department of Molecular Biology, Max Planck Institute for Molecular

Genetics, Berlin, Germany

 

July/02-Aug/03 Research Fellow

Department of Computing, Universidade de São Paulo (USP), São

Carlos-SP, Brazil

 

Nov/99-June/02 Visiting Professor

Centre of Informatics, Universidade Federal de Pernambuco (UFPE),

Recife-PE, Brazil

Teaching: Artificial Intelligence and Artificial Neural Networks courses for

undergraduate and graduate students (Computer Science).

Administration: Deputy research director (Centre of Informatics) from

Oct/01 - July/02.

 

RECENT GRANTS

 

2006-current Holder of an individual grant from CNPq for research productivity (Prime de Recherche pour le Maître de Conférence).

 

2009-current One of the main investigators for the international cooperation project “Advanced Machine Learning Techniques” (CAPES-FCT), involving researchers from Universidade de São Paulo at São Carlos, Universidade Federal de Pernambuco, Universidade do Porto (Portugal), among others.

 

2008-current Principal investigator for CNPq project “Meta-Learning: Clustering Algorithms and Analysis of Gene Expression Data Sets”, involving researchers from Universidade Federal de Pernambuco.

 

2008-current One of the main investigators for CNPq cooperation project “Development of Hybrid Intelligent Systems”, involving researchers from Federal University of Pernambuco, Universidade de São Paulo at São Carlos and Universidade Federal do Rio de Janeiro

 

RESEARCH

My research topics include Cluster Analysis (Non-Supervised Learning), Multi-Classifier Systems, Hybrid Intelligent Systems, and Bioinformatics. Recently, I have focused my work mainly on the analysis/development of Machine Learning techniques for Bioinformatics problems, such as clustering algorithms for analyzing microarray data. In the context of the research with Bioinformatics, I spent one year (Oct/2006-Sep/2007) as a visiting researcher at the Department of Computational Biology of the Max Planck Institute of Molecular Genetics, Berlin, Germany. I have, so far, published more than ten papers in journals and more than 50 papers in international conferences. Fourteen M.Sc. theses and two Ph.D. dissertations have been completed under my supervision. Since 2000 I have held a series of grants, initially, in the area of computability of artificial neural networks and, more recently, in the context of cluster analysis of microarray data. All the grants involve cooperation with researchers from several different universities: Universidade Federal do Rio de Janeiro, Universidade de São Paulo, Universidade Federal de Pernambuco, among others. Since August/2006 I hold a Brazilian grant equivalent to the French Prime de Recherche pour le Maître de Conférence. I have consistently served on the programme committee of the main Brazilian conferences on Artificial Intelligence, Neural Networks and Bioinformatics, respectively. In 2002 I was the programme chair of the Brazilian Symposium on Neural Networks. I have also participated in the program committee of international events, such as the Workshop Franco-Brésilien sur la Fouille de Données, the IEEE International Conference on Computational Science and Engineering, the Brain Inspired Cognitive Systems (BICS) Congress and the International Conference on Neural Information Processing (ICONIP). I was also Guest Editor of, respectively, the Journal of Intelligent and Fuzzy Systems, the International Journal of Neural Systems and the Neurocomputing.

 

LANGUAGES

Portuguese: mother tongue

English: fluent (written and spoken)

 

SELECTED PUBLICATIONS:

 

1. JOURNAL

1.1. FACELI, K.; SAKATA, T.; DE SOUTO, M. C. P.; DE CARVALHO, A. C. P. L. F. Selection Strategy for Set of

Clustering Solutions. Neurocomputing (Amsterdam), 2010. (Accepted to be published.)

1.2. FACELI, K.; DE SOUTO, M. C. .P.; DE ARAÚJO, D. S.A.; DE CARVALHO, A. C. P. L. F. Multi-objective

clustering ensemble for gene expression data analysis. Neurocomputing (Amsterdam), v. 72, p. 2763-2774, 2009.

1.3. DE SOUTO, M. C. .P.; COSTA, I. G. ; DE ARAÚJO, D. S.A; LUDERMIR, T. B.; SCHLIEP, A. Clustering cancer

gene expression data: a comparative study. BMC Bioinformatics, v. 9, p. 497-520, 2008.

1.4. FACELI, K. ; DE CARVALHO, A. C. P. L. F. ; DE SOUTO, M. C. P. Multi-objective Clustering Ensemble.

International Journal of Hybrid Intelligent Systems, v. 4, p. 145-156, 2007.

1.5. DE SOUTO, M. C. P. ; LUDERMIR, T. B. ; OLIVEIRA, W. R. Equivalence between RAM-based Neural Networks

and Probabilistic Automata. IEEE Transactions on Neural Networks, v. 16, n. 4, p. 996-999, 2005.

1.6. COSTA, I. G. ; DE CARVALHO, F. A. T. ; DE SOUTO, M. C. P. Comparative Analysis of Clustering Methods for

Gene Expression Time Series Data. Genetics and Molecular Biology, v. 27, n. 4, p. 623-631, 2004.

1.7. OLIVEIRA, W. R. ; DE SOUTO, M. C. P. ; LUDERMIR, T. B. Turing's Analysis of Computation and Artificial Neural

Networks. Journal of Intelligent and Fuzzy Systems, v. 13, n. 2/4, p. 85-98, 2003.

1.8. COSTA , I. G. ; DE CARVALHO, F. A. T. ; DE SOUTO, M. C. P. Comparative Study on Proximity indices for

Cluster Analysis of Gene Expression Time Series. Journal of Intelligent and Fuzzy Systems, v. 13, n. 2/4, p. 133-

142, 2003.

 

2. REFEREED CONFERENCES

2.1. COSTA, I. G.; LORENA, A. C. ; PERES, L. R. M.; DE SOUTO, M. C. .P. Using Supervised Complexity Measures

in the Analysis of Cancer Gene Expression Data Sets. Proc. of the Brazilian Symposium on Bioinformatics,

Lecture Notes on Computer Science, 2009. v. 5676. p. 48-59. (Best Paper Award)

2.2. OLIVEIRA, D. F.; CANUTO, A. M. P.; DE SOUTO, M. C. .P. The diversity/accuracy dilemma: An empirical analysis

in the context of heterogeneous ensembles. Proc. of the IEEE Congress on Evolutionary Computation (IEEE

CEC), 2009. p. 936-946.

2.3. NASCIMENTO, A.; PRUDENCIO, R. B. C. ; DE SOUTO, M. C. .P.; COSTA, I. G. Mining Rules for the Automatic

Selection Process of Clustering Methods Applied to Cancer Gene Expression Data. Proc. of the International

Conference on Artificial Neural Networks (ICANN), Lecture Notes on Computer Science, 2009. v. 5769. p. 20-29.

2.4. DE SOUTO, M. C. P ; PRUDENCIO, R. B. C.; SOARES, R. G. F. ; DE ARAÚJO, D. S. A. ; COSTA, I. G. ;

LUDERMIR, T. B. ; SCHLIEP, A. Ranking and Selecting Clustering Algorithms Using a Meta-learning Approach.

Proc. of the IEEE International Joint Conference on Neural Networks (IJCNN), 2008. p. 3728-3734.

2.5. OLIVEIRA, L. M. ; PARADEDA, R. B. ; CARVALHO, B. M. ; CANUTO, A. M. P. ; DE SOUTO, M. C. P. Particle

Detection on Electron Microscopy Micrographs using Multi-classifier Systems. Proc. of the International

Conference on Hybrid Intelligent Systems (HIS), 2007. p. 216-221.

2.6. DUTRA, T. F. S. ; CANUTO, A. M. P. ; DE SOUTO, M. C. P. . Using Weights as an Alternative to Decrease the

Dependency of the Combination-based Methods on the Ensemble Diversity. Proc. of the International Conference

on Neural Information Processing, Lecture Notes on Computer Science, 2006. v. 4232. p. 708-717