Abstraction based Output Range Analysis for Neural Networks

07/18/2020
by   Pavithra Prabhakar, et al.
0

In this paper, we consider the problem of output range analysis for feed-forward neural networks with ReLU activation functions. The existing approaches reduce the output range analysis problem to satisfiability and optimization solving, which are NP-hard problems, and whose computational complexity increases with the number of neurons in the network. To tackle the computational complexity, we present a novel abstraction technique that constructs a simpler neural network with fewer neurons, albeit with interval weights called interval neural network (INN), which over-approximates the output range of the given neural network. We reduce the output range analysis on the INNs to solving a mixed integer linear programming problem. Our experimental results highlight the trade-off between the computation time and the precision of the computed output range.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/22/2017

An approach to reachability analysis for feed-forward ReLU neural networks

We study the reachability problem for systems implemented as feed-forwar...
research
11/28/2018

The SWAG Algorithm; a Mathematical Approach that Outperforms Traditional Deep Learning. Theory and Implementation

The performance of artificial neural networks (ANNs) is influenced by we...
research
11/15/2021

Reachability analysis of neural networks using mixed monotonicity

This paper presents a new reachability analysis tool to compute an inter...
research
06/24/2020

DeepAbstract: Neural Network Abstraction for Accelerating Verification

While abstraction is a classic tool of verification to scale it up, it i...
research
06/09/2023

Complexity of Reachability Problems in Neural Networks

In this paper we investigate formal verification problems for Neural Net...
research
01/27/2023

Certified Invertibility in Neural Networks via Mixed-Integer Programming

Neural networks are notoriously vulnerable to adversarial attacks – smal...
research
02/21/2018

Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

The paper describes a new algorithm to generate minimal, stable, and sym...

Please sign up or login with your details

Forgot password? Click here to reset