Matheus R. F. Mendonça is currently a Phd candidate in
Computational Modeling at the National Laboratory for Scientific
Computing (LNCC), located in the city of Petrópolis, RJ, Brazil. In
2013, he received a B.Sc. degree in Exact Sciences, followed by a B.Sc.
degree in Computer Science in 2014 and a M.Sc. degree in Computer
Science in 2016, all obtained at the Federal University of Juiz de Fora
(UFJF), located in the city of Juiz de Fora, MG, Brazil. His research is
focused mainly in the application of Machine Learning methods for
solving problems from the Network Science research area. The main focus
of my current research are: Reinforcement Learning, Supervised Learning
(Neural Networks and Deep Learning models) and Network Centrality
analysis.
My main interests are Network Science and Machine Learning, with a focus
on Reinforcement Learning (RL) and Artificial Neural Networks (ANN).
More specifically, in RL, I am interested in (i) applying RL to real
world problems, (ii) studying and developing methods for identifying
macro-actions in RL, and (iii) developing RL architectures that work
well with deep neural networks (deep learning). I am also interested in
using supervised learning for graph analysis, such as node embedding and
predicting node features in large complex networks.