What’s in the Box?
Exploring the Inner Life of Neural Networks with Robust Rules
Jonas Fischer 1 Anna Olah 1 Jilles Vreeken 2
Abstract Y are typically active when neurons X are. For robustness
we explicitly allow for noise, and to ensure that we dis-
We propose a novel method for exploring how
cover a succinct yet descriptive set of rules that captures the
neurons withi ...


雷达卡




京公网安备 11010802022788号







