Can I read Opening the Black Box of Neural Nets: Case Studies in Stop/top Discrimination on EtoBox?

Opening the Black Box of Neural Nets: Case Studies in Stop/top Discrimination by Roxlo, Thomas; Reece, Matthew is a scholarly article available to read on EtoBox.

What is Opening the Black Box of Neural Nets: Case Studies in Stop/top Discrimination about?

We introduce techniques for exploring the functionality of a neural network and extracting simple, human-readable approximations to its performance. By performing gradient ascent on the input space of the network, we are able to produce large populations of artificial events which strongly excite a given classifier. By studying the populations of these events, we then directly produce what are essentially contour maps of the network's classification function. Combined with a suite of tools for identifying the input dimensions deemed most important by the network, we can utilize these maps to efficiently interpret the dominant criteria by which the network makes its classification. As a test case, we study networks trained to discriminate supersymmetric stop production in the dilepton channel from Standard Model backgrounds. In the case of a heavy stop decaying to a light neutralino, we find individual neurons with large mutual information with $m_{T2}^{\ell\ell}$, a human-designed variable for optimizing the analysis. The network selects events with significant missing $p_T$ oriented azimuthally away from both leptons, efficiently rejecting $t\overline{t}$ background. In the case o

Author

Roxlo, Thomas; Reece, Matthew

Published

2018

Language

EN