Skip to main content
Assured Autonomy Tools Portal
Continual Assurance of Learning-Enabled, Cyber-Physical Systems (LE-CPS)

Simplifying Neural Networks using Formal Verification

Abstract

Deep neural network (DNN) verification is an emerging field, with diverse verification engines quickly becoming available. Demonstrating the effectiveness of these engines on real-world DNNs is an important step towards their wider adoption. We present a tool that can leverage existing verification engines in performing a novel application: neural network simplification, through the reduction of the size of a DNN without harming its accuracy. We report on the work-flow of the simplification process, and demonstrate its potential significance and applicability on a family of real-world DNNs for aircraft collision avoidance, whose sizes we were able to reduce by as much as 10%.

Year of Publication
2019
Journal
arXiv e-prints
Number of Pages
arXiv:1910.12396
Date Published
oct