no code implementations • 15 Sep 2023 • Riccardo Massidda, Francesco Landolfi, Martina Cinquini, Davide Bacciu
The structure learning problem consists of fitting data generated by a Directed Acyclic Graph (DAG) to correctly reconstruct its arcs.
no code implementations • 22 Nov 2022 • Riccardo Massidda, Atticus Geiger, Thomas Icard, Davide Bacciu
Causal abstraction provides a theory describing how several causal models can represent the same system at different levels of detail.
no code implementations • 29 Sep 2021 • Riccardo Massidda, Davide Bacciu
Semantic alignment methods attempt to establish a link between human-level concepts and the units of an artificial neural network.