Integrating Learning and Reasoning with Deep Logic Models
This addresses the open problem of combining deep learning and reasoning for developing more intelligent agents, though it appears incremental as it builds on existing graphical models and relaxation techniques.
The paper tackles the integration of deep learning and probabilistic logic reasoning by proposing Deep Logic Models, an end-to-end differentiable architecture that embeds deep learners into a network with continuous logic relaxation, and the results show it overtakes limitations of other approaches in this area.
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. This paper presents 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 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.