The CIDEGENT research project I lead, called "Artificial General Intelligence: Beyond Deep Learning", intends to delve into Deep Learning and overcome the limitations it faces Today. Our approach is applying knowledge and techniques at the intersection of machine learning and computational neuroscience: we seek to adapt computationally efficient mechanisms of the brain into AI architectures, aiming for more powerful and explainable learning algorithms.

More particularly, we are testing the capabilities of the learning algorithm after introducing the following changes to the network: enhanced non-linearity of the network;  strengthened neurobiological substrate of the algorithm; and locally applied learning based on meta-learning principles. Using these techniques, we expect to improve the behavior of the algorithms in terms of flexibility, agility and robustness.

Within Neuroscience, we are highly interested in identifying physiological mechanisms of brain function and dysfunction, specifically in what relates to learning and cognition. To accomplish this, we simulate reinforcement learning models and biological neural networks. One of these studies focuses on cognitive dynamics, where we combine experimental procedures (psychophysics and neuroimaging) with computational approaches (machine learning and neural circuit modeling) to study the dynamics, development, and decline of human cognition across the life span.