Simplifying Neural Networks with the Marabou Verification Engine

10/25/2019

∙

by   Sumathi Gokulanathan, et al.

∙

0

∙

share

Deep neural network (DNN) verification is an emerging field, with diverse verification engines quickly becoming available. Demonstrating the effectiveness of these tools on real-world DNNs is an important step towards their wider adoption. We focus here on the recently proposed Marabou verification tool, and demonstrate its usage for a novel application: simplifying neural networks, by reducing the size of a DNN without harming its accuracy. We report on the work-flow of the simplification process, and on its potential significance and applicability to domains of interest.