paper-with-me

Papers

Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks

2017-08-09 · Weiming Xiang, Hoang-Dung Tran, Taylor T. Johnson

In this paper, the output reachable estimation and safety verification problems for multi-layer perceptron neural networks are addressed. First, a conception called maximum sensitivity in introduced and, for a class of multi-layer perceptrons whose activation functions are monotonic functions, the maximum sensitivity can be computed via solving convex optimization problems. Then, using a simulation-based method, the output reachable set estimation problem for neural networks is formulated into a chain of optimization problems. Finally, an automated safety verification is developed based on the output reachable set estimation result. An application to the safety verification for a robotic arm model with two joints is presented to show the effectiveness of proposed approaches.

📄 PDF Abstract BibTeX arXiv:1708.03322

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations

2017-12-21 · Weiming Xiang, Hoang-Dung Tran, Taylor T. Johnson

Neural networks have been widely used to solve complex real-world problems. Due to the complicate, nonlinear, non-convex nature of neural networks, formal safety guarantees for the output behaviors of neural networks wil…

Reachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approach

2020-04-26 · Weiming Xiang, Hoang-Dung Tran, Xiaodong Yang, Taylor T. Johnson

The vulnerability of artificial intelligence (AI) and machine learning (ML) against adversarial disturbances and attacks significantly restricts their applicability in safety-critical systems including cyber-physical sys…

Contraction-Guided Adaptive Partitioning for Reachability Analysis of Neural Network Controlled Systems

2023-04-07 · Akash Harapanahalli, Saber Jafarpour, Samuel Coogan

In this paper, we present a contraction-guided adaptive partitioning algorithm for improving interval-valued robust reachable set estimates in a nonlinear feedback loop with a neural network controller and disturbances. …

Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Components

2020-11-23 · Joseph A. Vincent, Mac Schwager

We present a method for computing exact reachable sets for deep neural networks with rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety analysis of robotic perception and contro…

Constrained Feedforward Neural Network Training via Reachability Analysis

2021-07-16 · Long Kiu Chung, Adam Dai, Derek Knowles, Shreyas Kousik 외

Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge …