Re:A New Approach to Understanding How Machines Think
by ssivark on Monday January 28, 2019 @12:34AM
(#19015505)
I found it easier to understand the idea by skimming the introduction in the paper [1]:
> TCAV uses directional derivatives to quantify the model prediction’s sensitivity to an underlying high-level concept [...] For instance, given an ML image model recognizing zebras, and a new, user-defined set of examples defining ‘striped’, TCAV can quantify the influence of striped concept to the ‘zebra’ prediction as a single number. In addition, we conduct statistical tests where CAVs are randomly re-learned and rejected unless they show a significant and stable correlation with a model output class or state value.
> TCAV uses directional derivatives to quantify the model prediction’s sensitivity to an underlying high-level concept [...] For instance, given an ML image model recognizing zebras, and a new, user-defined set of examples defining ‘striped’, TCAV can quantify the influence of striped concept to the ‘zebra’ prediction as a single number. In addition, we conduct statistical tests where CAVs are randomly re-learned and rejected unless they show a significant and stable correlation with a model output class or state value.
[1]: https://arxiv.org/abs/1711.11279