About Me
Hello there.
My name’s Mateus and I’m a researcher in Machine Learning applied for Wireless Communications. My current research involves ML solutions for semantic and goal-oriented communications.
My PhD research was focused on multi-agent reinforcement learning for protocol emergence, by jointly learning a resource management policy and the associated signalling.
My Masters research was focused in reinforcement learning based solutions applied in 5G scenarios.
Aside from machine learning, I also have knowledge in Business Intelligence and Data Analysis from a graduate studies course.
My main interests are Deep Reinforcement Learning, Semmantic and Goal-oriented communications, Link Adaptation techniques and PHY/MAC layers.
Selected Publications
Adaptive Modulation and Coding based on Reinforcement Learning for 5G Networks
ieeexplore.ieee.org/document/9024384We design a self-exploratory reinforcement learning (RL) framework, based on the Q-learning algorithm, that enables the base station (BS) to choose a suitable modulation and coding scheme (MCS) that maximizes the spectral efficiency while maintaining a low block error rate (BLER).
Published in 2019 IEEE Globecom Workshops (GC Wkshps).
The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning
https://arxiv.org/abs/2108.07144We propose a new framework, exploiting the multi-agent deep deterministic policy gradient (MADDPG) algorithm, to enable a base station (BS) and user equipment (UE) to come up with a medium access control (MAC) protocol in a multiple access scenario
Accepted for the 2021 IEEE Globecom Workshops (GC Wkshps).
Experience
CEA-Leti is a research institute for electronics and information technologies. It is one of the world's largest organizations for applied research in microelectronics and nanotechnology.
Current research involves the application of Machine Learning to Semantic and Goal-Oriented wireless communications.
Member of the 6G-GOALS Project (link)
Nokia Bell Labs is the world-renowned industrial research arm of Nokia, having invented many of the foundational technologies that underpin information and communications networks and all digital devices and systems.
Development of MARL solutions for automated protocol design in wireless networks.
Member of the WindMill Project, an European Training Network (ETN) project, within the framework of the H2020 Marie Skłodowska-Curie Innovative Training Networks (ITNs).
Nokia Bell Labs France
https://www.bell-labs.com/Early Stage Researcher
September 2020 - September 2023
The GTEL-UFC is a research center with knowledge about wireless telecommunications and provides this knowledge in technical and scientific partnerships with public and private entities, notably through research and development projects.
Development of a Reinforcement Learning solution to Link Adaptation in 5G systems.
Development of a Python simulator in compliance with T.S. 38.212 and T.S 38.214.
Published the paper “Adaptive Modulation and Coding based on Reinforcement Learning for 5G Networks” at 2019 IEEE Globecom Workshop on Machine Learning for Wireless Communications
Education
Institut National des Sciences Appliquées de Lyon (INSA Lyon)
PhD in Telecommunications Engineering
September 2020 - January 2024
Ranked as the 10° best Engineering School in France by the L'étudiant 2021 ranking.
Research on Reinforcement Learning applied to Mobile Networks.
My PhD studies involve the study of deep reinforcement learning applied to radio resource management problems.
Thesis: Protocol Emergence with Multi-Agent Reinforcement Learning link
Ranked as the 19° best university in the Latin America by the Times Higher Education 2019 ranking.
Research on Machine Learning and Big Data applied to 5G Networks.
My master thesis involves the study of reinforcement learning based solutions to the link adaptation problem.
Federal University of Ceará
MSc in Telecommunications Engineering
February 2018 - March 2020
Centro Universitário 7 de Setembro
Graduate Studies in Data Science
September 2017 - February 2020
Specialization studies in Business Intelligence, Big Data and Data Analytics.
Ranked as the 19° best university in the Latin America by the Times Higher Education 2019 ranking.
My bachelor thesis was on the study on Machine Learning solutions applied to Indoor Localization Problem, devising a 3D WLAN Indoor Localization System based on RSSI fingerprints.
Federal University of Ceará
BSc Telecommunications Engineering
January 2010 - July 2017
SUPÉLEC
Exchange Program in Electrical Engineering
September 2012 - July 2013
CentraleSupélec is widely considered to be among the top 2 engineering schools of France.
One year exchange studies under the BRAFITEC program.
Skills
Spoken Languages: Portuguese (native), English (Full Professional), French (Professional).
Software: LaTeX, Git, MATLAB, Office Suites, Tableau, Power BI.
Programming: Python, SQL
Frameworks and Libraries: Scikit-Learn, Keras, Pytorch, Bokeh