Simplifying Neural Networks using Formal Verification

Autor:	Gokulanathan, Sumathi, Feldsher, Alexander, Malca, Adi, Barrett, Clark, Katz, Guy
Rok vydání:	2019
Předmět:	Computer Science - Logic in Computer Science Computer Science - Machine Learning Computer Science - Neural and Evolutionary Computing
Druh dokumentu:	Working Paper
Popis:	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%. Comment: This paper appeared at NFM 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1910.12396 Zobrazit plný text záznamu View this record from Arxiv