The Computational Complexity of Understanding Binary Classifier Decisions

For a d-ary Boolean function Φ: {0, 1}d → {0, 1} and an assignment to its variables x = (x1, x2, . . . , xd) we consider the problem of finding those subsets of the variables that are sufficient to determine the function value with a given probability δ. This is motivated by the task of interpreting...

Full description

Bibliographic Details

Published in:	The Journal of artificial intelligence research Vol. 70; p. 351
Main Authors:	Waeldchen, Stephan, Macdonald, Jan, Hauch, Sascha, Kutyniok, Gitta
Format:	Journal Article
Language:	English
Published:	San Francisco AI Access Foundation 21.01.2021
Subjects:	Algorithms Approximation Artificial intelligence Boolean Boolean algebra Boolean functions Classifiers Complexity Neural networks Polynomials
ISSN:	1076-9757, 1076-9757, 1943-5037
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!