Abstraction based Output Range Analysis for Neural Networks

by   Pavithra Prabhakar, et al.
Kansas State University

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.


page 1

page 2

page 3

page 4


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

We study the reachability problem for systems implemented as feed-forwar...

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...

Reachability analysis of neural networks using mixed monotonicity

This paper presents a new reachability analysis tool to compute an inter...

DeepAbstract: Neural Network Abstraction for Accelerating Verification

While abstraction is a classic tool of verification to scale it up, it i...

Complexity of Reachability Problems in Neural Networks

In this paper we investigate formal verification problems for Neural Net...

Certified Invertibility in Neural Networks via Mixed-Integer Programming

Neural networks are notoriously vulnerable to adversarial attacks – smal...

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