5 citations · 8 across the 2 of their papers we have counts for
2 papers
cs.LG2021★ 3 cited
Defining and Quantifying the Emergence of Sparse Concepts in DNNs
Jie Ren, Mingjie Li, Qirui Chen +2
This paper aims to illustrate the concept-emerging phenomenon in a trained DNN. Specifically, we find that the inference score of a DNN can be disentangled into the effects of a fe…
cs.LG2021★ 5 cited
Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?
Jie Ren, Zhanpeng Zhou, Qirui Chen +1
Masking some input variables of a deep neural network (DNN) and computing output changes on the masked input sample represent a typical way to compute attributions of input variabl…