activity
20192025
collaborators

11 papers

cs.AI2025

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

Emanuele Marconato, Samuele Bortolotti, Emile van Krieken +6

Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g. safety or structural constraints. As such, it represents…

cs.LG2025

Efficient Preimage Approximation for Neural Network Certification

Anton Björklund, Mykola Zaitsev, Paolo Morettin +1

The growing reliance on artificial intelligence in safety- and security-critical applications is raising concerns about the robustness of neural networks to erroneous or adversaria…

cs.LG2025

A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction

Leander Kurscheidt, Paolo Morettin, Roberto Sebastiani +2

In safety-critical applications, guaranteeing the satisfaction of constraints over continuous environments is crucial, e.g., an autonomous agent should never crash into obstacles o…

cs.LG2025

Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens

Samuele Bortolotti, Emanuele Marconato, Paolo Morettin +2

Concept-based Models are neural networks that learn a concept extractor to map inputs to high-level concepts and an inference layer to translate these into predictions. Ensuring th…

cs.LG2024

A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts

Samuele Bortolotti, Emanuele Marconato, Tommaso Carraro +5

The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning. These problems are critical for understanding important prope…

cs.LG2024

Semantic Loss Functions for Neuro-Symbolic Structured Prediction

Kareem Ahmed, Stefano Teso, Paolo Morettin +8

Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the in…