AI Chat AI Image Generator AI Video Text to Speech

A Toolbox for Fast Interval Arithmetic in numpy with an Application to Formal Verification of Neural Network Controlled Systems

06/27/2023

∙

by Akash Harapanahalli, et al.

∙

∙

In this paper, we present a toolbox for interval analysis in numpy, with an application to formal verification of neural network controlled systems. Using the notion of natural inclusion functions, we systematically construct interval bounds for a general class of mappings. The toolbox offers efficient computation of natural inclusion functions using compiled C code, as well as a familiar interface in numpy with its canonical features, such as n-dimensional arrays, matrix/vector operations, and vectorization. We then use this toolbox in formal verification of dynamical systems with neural network controllers, through the composition of their inclusion functions.

Akash Harapanahalli
5 publications
Saber Jafarpour
11 publications
Samuel Coogan
14 publications

page 1

page 2

page 3

page 4

research

∙ 01/19/2023

Interval Reachability of Nonlinear Dynamical Systems with Neural Network Controllers

This paper proposes a computationally efficient framework, based on inte...

0 Saber Jafarpour, et al. ∙

research

∙ 09/16/2023

Forward Invariance in Neural Network Controlled Systems

We present a framework based on interval analysis and monotone systems t...

0 Akash Harapanahalli, et al. ∙

research

∙ 07/27/2023

Efficient Interaction-Aware Interval Analysis of Neural Network Feedback Loops

In this paper, we propose a computationally efficient framework for inte...

0 Saber Jafarpour, et al. ∙

research

∙ 07/04/2021

Interval probability density functions constructed from a generalization of the Moore and Yang integral

Moore and Yang defined an integral notion, based on an extension of Riem...

0 Benjamin Bedregal, et al. ∙

research

∙ 06/25/2021

POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems

We propose POLAR, a polynomial arithmetic framework that leverages polyn...

0 Chao Huang, et al. ∙

research

∙ 06/26/2023

Verification of Neural Network Control Systems using Symbolic Zonotopes and Polynotopes

Verification and safety assessment of neural network controlled systems ...

0 Carlos Trapiello, et al. ∙

research

∙ 03/05/2020

Validation of Image-Based Neural Network Controllers through Adaptive Stress Testing

Neural networks have become state-of-the-art for computer vision problem...

0 Kyle D. Julian, et al. ∙