aspBEEF: Explaining Predictions Through Optimal Clustering
Keyword(s):
In this paper we introduce aspBEEF, a tool for generating explanations for the outcome of an arbitrary machine learning classifier. This is done using Grover’s et al. framework known as Balanced English Explanations of Forecasts (BEEF) that generates explanations in terms of in terms of finite intervals over the values of the input features. Since the problem of obtaining an optimal BEEF explanation has been proved to be NP-complete, BEEF existing implementation computes an approximation. In this work we use instead an encoding into the Answer Set Programming paradigm, specialized in solving NP problems, to guarantee that the computed solutions are optimal.
2018 ◽
Vol 20
(2)
◽
pp. 205-224
◽
Keyword(s):
2006 ◽
Vol 6
(1-2)
◽
pp. 23-60
◽
2020 ◽
Vol 20
(6)
◽
pp. 911-925
2019 ◽
Vol 33
◽
pp. 1933-1940
◽
Keyword(s):
2015 ◽
Vol 16
(4)
◽
pp. 465-497
◽
2015 ◽
Vol 15
(4-5)
◽
pp. 495-510
◽
2013 ◽
Vol 14
(6)
◽
pp. 841-868
◽