Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Budzik, Jay"'
We compare machine learning explainability methods based on the theory of atomic (Shapley, 1953) and infinitesimal (Aumann and Shapley, 1974) games, in a theoretical and experimental investigation into how the model and choice of integration path can
Externí odkaz:
http://arxiv.org/abs/2007.04169
We introduce Generalized Integrated Gradients (GIG), a formal extension of the Integrated Gradients (IG) (Sundararajan et al., 2017) method for attributing credit to the input variables of a predictive model. GIG improves IG by explaining a broader v
Externí odkaz:
http://arxiv.org/abs/1909.01869
Autor:
Budzik, Jay1 partner@zestfinance.com
Publikováno v:
Credit Union Times. 10/9/2019, Vol. 30 Issue 34, p1-3. 3p.
Publikováno v:
In International Journal of Human - Computer Studies January 2002 56(1):47-74
Publikováno v:
Proceedings of the 13th International World Wide Web Conference: Alternate Track Papers & Posters; 5/19/2004, p41-47, 7p
Publikováno v:
Proceedings of the 11th International Conference: World Wide Web; 5/ 7/2002, p726-735, 10p
Publikováno v:
Proceedings of the 7th International Conference: Intelligent User Interfaces; 1/13/2002, p79-86, 8p
Publikováno v:
Proceedings of the 6th International Conference: Intelligent User Interfaces; Jan2001, p49-52, 4p
Autor:
Budzik, Jay (AUTHOR), Hammond, Kristian (AUTHOR)
Publikováno v:
Proceedings of the ASIS Annual Meeting. 10/31/1999, Vol. 62, p727-740. 14p.