Bounding and Counting Linear Regions of Deep Neural Networks — mentioned by sdenton4

Tue, 26 Feb 2019 02:56:04 GMT

+1. Looking quickly at the backing paper, it's all about higher-order derivatives. As I see it, the grindy-axe is about where and how one makes the hand-off from algebraic notation to actual computation: keeping the calculation in algebraic form allows efficient algebraic manipulations, which can then be translated into low-level computations. The question, then, is: a) whether the space of problems where you have good algebraic notation lines up well with the total scope of TF problems, and b) whether the extra complexity of supporting the full computer algebra system is 'worth it.' For the…

Paper and discussion history. A mention is not an endorsement.

Bounding and Counting Linear Regions of Deep Neural Networks · HackerPapers discussions

Bounding and Counting Linear Regions of Deep Neural Networks — mentioned by sdenton4