https://arxiv.org/abs/2107.00793 The Causal-Neural Connection: Expressiveness, Learnability, and Inference One of the central elements of any causal inference is an object called structural causal model (SCM), which represents a collection of mechanisms and exogenous sources of random variation of the system under investigation (Pearl, 2000). An important property of many kinds of neural networks is univ... arxiv.org 저자 : Kevin Xia, Kai-Zhan Lee, Yoshua Bengio, Elias Bareinboim 실린 곳 : NIPS 2021 ...
#
causal과딥러닝의만남
#
간만에재밌게읽은논문
#
거장들의논문