Education

• PhD in Data Science
• September/2018 - Present

• Université Paris-Saclay & CEA

Thesis Title: Optimal Transport for Domain Adaptation with Applications to Bacteria Stain Classification
Advisor: Antoine Souloumiac & Fred Maurice Ngolè Mboula

• Master's Degree in Electronic Engineering and Industrial Informatics
• September/2018 - August/2020

• Institut National des Sciences Appliquées de Rennes, Rennes, France
• GPA: 17.26/20.00

Thesis Title: Optimal Transport for Domain Adaptation with Applications to Bacteria Stain Classification
Advisor: Fred Maurice Ngolè Mboula

• Bachelor's Degree in Computer Engineering
• January/2015 - April/2021

• Universidade Federal do Ceará, Fortaleza, Brazil
• GPA: 8.95/10.00

Thesis Title: Cross-Domain Fault Diagnosis through Optimal Transport
Advisor: Michela Mulas

Professional Experience

Comissariat pour l’Énergie Atomique et aux Énergies Alternatives, Giff-Sur-Yvette, France

• PhD Student
• October 2021 - Present

During this internship I was in charge of implementing Optimal Transport for Domain Adaptation methods for a problem involving transfer learning on the classification of bacteria cell stain.
Supervisor: Fred-Maurice Ngolè Mboula

Dell Lead, Fortaleza, Brazil

• Scientific Researcher in Data Mining
• April 2021 - September 2021

Responsible for mining textual data and creating data visualizations.

Comissariat pour l’Énergie Atomique et aux Énergies Alternatives, Giff-Sur-Yvette, France

• Research Intern in Artificial Intelligence
• March 2020 - August 2020

During this internship I was in charge of implementing Optimal Transport for Domain Adaptation methods for a problem involving transfer learning on the classification of bacteria cell stain.
Supervisor: Fred-Maurice Ngolè Mboula

Institut d’Electronique et des Technologies du Numérique, groupe VAADER, Rennes, France

• Research Intern in Deep Learning
• March 2020 - August 2020

During this internship I was responsible for implementing a benchmark for comparing image denoising methods. A special focus was given to deep neural network methods. The benchmark is Open Source, and its code is hosted on Github
Supervisor: Florian Lemarchand

Programming Skills

Programming Languages

Python, Matlab (+++)
C++/C (++)
Javascript, VHDL (+)

Toolboxes and Libraries

Python: Tensorflow (+++), Python Optimal Transport (+++), Pytorch (++)
Matlab: Simulink (++), Deep Learning Toolbos (++)

Other Software

Others: Tableau, Latex, HTML

Languages

Portuguese (Mother Tongue)
English (B2/Advanced)
French (B2/Advanced)

Publications

1. Fernandes Montesuma, Eduardo, Levi PSA Alencar, and Guilherme A. Barreto. Avaliação de Algoritmos de Classificação de Padrões na Detecção de Câncer do Colo do Útero. [Bibtex] [Paper]
2. Lemarchand, F., Fernandes Montesuma, Eduardo, Pelcat, M., & Nogues, E. (2020, May). OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2648-2652). IEEE. [Bibtex] [Arxiv] [Code]
3. Fernandes Montesuma, Eduardo, & Mboula, F. M. N. (2021, June). Wasserstein Barycenter Transport for Acoustic Adaptation. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3405-3409). [IEEE Explore] [Code]
4. Fernandes Montesuma, Eduardo, & Mboula, F. (2021). Wasserstein Barycenter for Multi-Source Domain Adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 16785-16793). [The CVF Open Access] [Paper] [Supplementary] [Code]
5. Fernandes Montesuma, Eduardo, et al. “An Empirical Study of Information Retrieval and Machine Reading Comprehension Algorithms for an Online Education Platform.” Anais do XIII Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana. SBC, 2021. [Paper]
6. Fernandes Montesuma, Eduardo, Mulas, M., Corona, F., and Mboula, F. M. N. (2022). Cross-domain fault diagnosis through optimal transport for a CSTR process. IFAC-PapersOnLine, 55(7), 946-951. [Paper] [Code]
7. Fernandes Montesuma, Eduardo, Mboula, F. N., & Souloumiac, A. (2023). Recent advances in optimal transport for machine learning. arXiv preprint arXiv:2306.16156. [Paper]
8. Fernandes Montesuma, Eduardo, Ngolè Mboula, Fred Maurice, and Souloumiac, Antoine (2023). Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space. 26th European Conference on Artificial Intelligence [Paper]

Scholarships and Awards

From September/2018 to Ferbuary/2020 I had the opportunity to have my double degree studies in France funded by Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), with a BRAFITEC Scolarship