Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Villadsen, Lea"'
Self-explainable deep neural networks are a recent class of models that can output ante-hoc local explanations that are faithful to the model's reasoning, and as such represent a step forward toward filling the gap between expressiveness and interpre
Externí odkaz:
http://arxiv.org/abs/2308.15096
