Much of the progress in the task of extracting knowledge from data is obtained through research in machine learning. Two sub-areas of ML are of particular interest in this research project: (i) Deep Learning and (ii) Reinforcement Learning.
Deep Learning encompasses a set of techniques created to simulate the behavior of the human brain in tasks such as visual recognition, speech recognition, and natural language processing. These techniques attempt to produce high-level hierarchical representations from input data through layers of sequential processing.
Reinforcement learning studies how software agents can learn to perform actions rationally in an environment to maximize their reward. Learning in this context takes place by providing the agent with reinforcement signals (which can be negative or positive) associated with the actions selected by the agent. RL can be applied to various tasks, such as planning, task scheduling, games, and more.
- Diego Haddad
- Eduardo Bezerra (Leader)
- Pedro Gonzalez
International partnerships with researchers from the University of Memphis, USA; Institute for Research in Fundamental Sciences, Iran, and the University of Aveiro, Portugal.