Learn to Explain Efficiently via Neural Logic Inductive Learning

ICLR, 2020.

Cited by: 1|Views1102
EI
Weibo:
We propose Neural Logic Inductive Learning, a differentiable inductive logic programming framework that learns explanatory rules from data

Abstract:

The capability of making interpretable and self-explanatory decisions is essential for developing responsible machine learning systems. In this work, we study the learning to explain the problem in the scope of inductive logic programming (ILP). We propose Neural Logic Inductive Learning (NLIL), an efficient differentiable ILP framework t...More
Your rating :
0

 

Tags
Comments