A novel paper accepted on Neuro Symbolic AI accepted @ NeSy23

On Apr. 27, Luigi Capogrosso and Francesco Taioli, national PhD students in AI at Polytechnic of Turin in collaboration with the University of Verona, received the good news! The paper “Designing Logic Tensor Networks for Visual Sudoku puzzle classification” has been accepted at 17th INTERNATIONAL WORKSHOP ON NEURAL-SYMBOLIC LEARNING AND REASONING.

Given the increasing importance of the neurosymbolic (NeSy) approach in artificial intelligence, there is a growing interest in studying benchmarks specifically designed to emphasize the ability of AI systems to combine low-level representation learning with high-level symbolic reasoning. One such recent benchmark is Visual Sudoku Puzzle Classification, which combines visual perception with relational constraints. In this work, we investigate the application of Logic Tensork Networks (LTNs) to the Visual Sudoku Classification task and discuss various alternatives regarding logical constraint formulation, integration with the perceptual module and training procedure.

The paper was born after the two students followed the Neuro-Symbolic course offered by the Polytechnic of Turin. The work is a collaboration between the students of the University of Milano-Bicocca, Polytechnic of Turin, University of Verona, and LINKS Foundation.

The authors are tackling this from a pedagogical point of view, specifying all the logic behind the problem formalization, formulating and integrating logical constraints to perform the chosen tasks.

Link to the workshop: Nesy 2023

Lascia un commento

Il tuo indirizzo email non sarà pubblicato. I campi obbligatori sono contrassegnati *