Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Persia, Cosimo Damiano"'
Autor:
Di Francescomarino, Chiara, Ghidini, Chiara, Maggi, Fabrizio Maria, Rizzi, Williams, Persia, Cosimo Damiano
A characteristic of existing predictive process monitoring techniques is to first construct a predictive model based on past process executions, and then use it to predict the future of new ongoing cases, without the possibility of updating it with n
Externí odkaz:
http://arxiv.org/abs/1804.03967
Autor:
Persia, Cosimo Damiano, Ozaki, Ana
Publikováno v:
Proceedings of the Northern Lights Deep Learning Workshop; Vol. 3 (2022): Proceedings of the Northern Lights Deep Learning Workshop 2022
Proceedings of the Northern Lights Deep Learning Workshop
Proceedings of the Northern Lights Deep Learning Workshop
We investigate the problem of extracting rules, expressed in Horn logic, from neural network models. Our work is based on the exact learning model, in which a learner interacts with a teacher (the neural network model) via queries in order to learn a