News for hackers. Stuff that matters.
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.

[1]: https://arxiv.org/abs/1711.11279

Re:A New Approach to Understanding How Machines Think by cs702 on Monday January 28, 2019 @09:25AM (#19017591)
Me too. Thank you for posting the link.