Francesco Giannini (DIISM, University of Siena)

Mar 13, 2019 – 11:00 AM

DIISM, Artificial Intelligence laboratory (room 201), Siena SI

Description

Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with
high dimensional input patterns. Probabilistic logic reasoning, on the other hand, is capable to take consistent and robust decisions in
complex environments. The integration of deep learning and logic reasoning is still an open-research problem and it is considered to be
the key for the development of real intelligent agents. In this talk, we present Deep Logic Models, which are deep graphical models integrating deep learning and logic reasoning both for learning and inference. Deep Logic Models create an end-to-end differentiable architecture, where deep learners are embedded into a network implementing a continuous relaxation of the logic knowledge. The learning process allows us to jointly learn the weights of the deep learners and the meta-parameters controlling the high-level reasoning. The experimental results show that the proposed methodology overtakes the limitations of the other approaches that have been proposed to bridge deep learning and reasoning.