71 citations · 229 across the 21 of their papers we have counts for
3 papers · 1 filter
A Neural Rewriting System to Solve Algorithmic Problems
Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti
Modern neural network architectures still struggle to learn algorithmic procedures that require to systematically apply compositional rules to solve out-of-distribution problem ins…
A Hybrid System for Systematic Generalization in Simple Arithmetic Problems
Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti
Solving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence. However, symbolic reasoning is s…
Investigating the generative dynamics of energy-based neural networks
Lorenzo Tausani, Alberto Testolin, Marco Zorzi
Generative neural networks can produce data samples according to the statistical properties of their training distribution. This feature can be used to test modern computational ne…