An approach to reachability analysis for feed-forward ReLU neural networks
Artificial Intelligence
2017-06-23 v1 Machine Learning
Logic in Computer Science
Abstract
We study the reachability problem for systems implemented as feed-forward neural networks whose activation function is implemented via ReLU functions. We draw a correspondence between establishing whether some arbitrary output can ever be outputed by a neural system and linear problems characterising a neural system of interest. We present a methodology to solve cases of practical interest by means of a state-of-the-art linear programs solver. We evaluate the technique presented by discussing the experimental results obtained by analysing reachability properties for a number of benchmarks in the literature.
Keywords
Cite
@article{arxiv.1706.07351,
title = {An approach to reachability analysis for feed-forward ReLU neural networks},
author = {Alessio Lomuscio and Lalit Maganti},
journal= {arXiv preprint arXiv:1706.07351},
year = {2017}
}