Marcelo Arenas, Daniel Baez, Pablo Barcelo, Jorge Perez, and Bernardo Subercaseaux. Foundations of Symbolic Languages for Model Interpretability. In Proceedings of the 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021), Virtual Event, 2021. (2021)

Foundations of Symbolic Languages for Model Interpretability

Revista : CONFERENCIA A*: NeurIPS 2021 (Annual Conference on Neural Information Processing Systems)
Tipo de publicación : Conferencia No DCC Ir a publicación

Foundations of Symbolic Languages for Model Interpretability

Abstract