Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Tsanakas, T."'
A vastly growing literature on explaining deep learning models has emerged. This paper contributes to that literature by introducing a global gradient-based model-agnostic method, which we call Marginal Attribution by Conditioning on Quantiles (MACQ)
Externí odkaz:
http://arxiv.org/abs/2103.11706
