About: NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
title	NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems
Creator	Nguyen, Wang, C Yang, Xiaodong Bak, Stanley Johnson, Taylor Lahiri, S Luan, Viet Manzanas Lopez, Diego Musau, Patrick Tran, H.-D Tran, Hoang-Dung Xiang, Weiming
source	PMC
abstract	This paper presents the Neural Network Verification (NNV) software tool, a set-based verification framework for deep neural networks (DNNs) and learning-enabled cyber-physical systems (CPS). The crux of NNV is a collection of reachability algorithms that make use of a variety of set representations, such as polyhedra, star sets, zonotopes, and abstract-domain representations. NNV supports both exact (sound and complete) and over-approximate (sound) reachability algorithms for verifying safety and robustness properties of feed-forward neural networks (FFNNs) with various activation functions. For learning-enabled CPS, such as closed-loop control systems incorporating neural networks, NNV provides exact and over-approximate reachability analysis schemes for linear plant models and FFNN controllers with piecewise-linear activation functions, such as ReLUs. For similar neural network control systems (NNCS) that instead have nonlinear plant models, NNV supports over-approximate analysis by combining the star set analysis used for FFNN controllers with zonotope-based analysis for nonlinear plant dynamics building on CORA. We evaluate NNV using two real-world case studies: the first is safety verification of ACAS Xu networks, and the second deals with the safety verification of a deep learning-based adaptive cruise control system.
has issue date	2020-06-13(xsd:dateTime)
bibo:doi	10.1007/978-3-030-53288-8_1
has license	cc-by
sha1sum (hex)	072aad2256f4642d7e59accdb5c20edfe787a488
schema:url	https://doi.org/10.1007/978-3-030-53288-8_1
resource representing a document's title	NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems
has PubMed Central identifier	PMC7363192
schema:publication	Computer Aided Verification
resource representing a document's body	covid:072aad2256f4642d7e59accdb5c20edfe787a488#body_text
is schema:about of	named entity 'models' named entity 'Verification' named entity 'models' named entity 'CONTROLLERS' named entity 'HAVE' named entity 'APPROXIMATE' named entity 'SECOND' covid:arg/072aad2256f4642d7e59accdb5c20edfe787a488 named entity 'representations' named entity 'supports' named entity 'case studies' named entity 'deep' named entity 'activation' named entity 'presents' named entity 'network' named entity 'piecewise-linear' named entity 'deals' named entity 'reachability' named entity 'sets' named entity 'Systems' named entity 'CPS' named entity 'CPS' named entity 'activation functions' named entity 'neural network' named entity 'set-based' named entity 'control systems' named entity 'Neural Network' named entity 'Tool' named entity 'Cyber-Physical Systems' named entity 'exact' named entity 'nonlinear model' named entity 'ReLU' named entity 'algorithm' named entity 'mixed-integer linear programming' named entity 'non-empty' named entity 'activation function' named entity 'CNN' named entity 'algorithm' named entity 'polyhedron' named entity 'ACC' named entity 'linear model' named entity 'optimization problems' named entity 'ACC' named entity 'neural network' named entity 'affine mapping' named entity '64-bit' named entity 'DNN' named entity 'computationally expensive' named entity 'predicate' named entity 'algorithm' named entity 'zero-order hold' named entity 'relative velocity' named entity 'computation time' named entity 'activation functions' named entity 'ACAS' named entity 'zonotope' named entity 'software tool' named entity 'computing' named entity 'input set' named entity 'feedforward neural networks' named entity 'fully connected' named entity 'Hybrid Systems' named entity 'multi-core' named entity 'Neural Network' named entity 'algorithm' named entity 'inference' named entity 'neural network' named entity 'Intel Core' named entity 'ReLU' named entity 'reachability analysis' named entity 'zonotope' named entity 'Tensorflow'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software