Log In Sign Up

Integrating Learning and Reasoning with Deep Logic Models

by   Giuseppe Marra, et al.

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.


page 1

page 2

page 3

page 4


Relational Neural Machines

Deep learning has been shown to achieve impressive results in several ta...

LYRICS: a General Interface Layer to Integrate AI and Deep Learning

In spite of the amazing results obtained by deep learning in many applic...

Machine Learning is Abduction Inference

Concept of Abduction with Gradated Contradictions is introduced here as ...

TensorLog: Deep Learning Meets Probabilistic DBs

We present an implementation of a probabilistic first-order logic called...

LAGNet: Logic-Aware Graph Network for Human Interaction Understanding

Compared with the progress made on human activity classification, much l...

Logic could be learned from images

Logic reasoning is a significant ability of human intelligence and also ...

Exploring End-to-End Differentiable Natural Logic Modeling

We explore end-to-end trained differentiable models that integrate natur...