ISO/IEC 24029-2:2023
Artificial intelligence (AI) — Assessment of the robustness of neural networks — Part 2: Methodology for the use of formal methods
This document provides methodology for the use of formal methods to assess robustness properties of neural networks. The document focuses on how to select, apply and manage formal methods to prove robustness properties.
| Get this standard | Prices exclude GST | |
|---|---|---|
| PDF ( Single user document) |
$256.00 NZD
|
|
| HardCopy |
$303.00 NZD
|
|
| Networkable PDF |
Price varies
|
Foreword
Introduction
1 Scope
2 Normative references
3 Terms and definitions
4 Abbreviated terms
5 Robustness assessment
5.1 General
5.2 Notion of domain
5.3 Stability
5.3.1 Stability property
5.3.2 Stability criterion
5.4 Sensitivity
5.4.1 Sensitivity property
5.4.2 Sensitivity criterion
5.5 Relevance
5.5.1 Relevance property
5.5.2 Relevance criterion
5.6 Reachability
5.6.1 Reachability property
5.6.2 Reachability criterion
6 Applicability of formal methods on neural networks
6.1 Types of neural network concerned
6.1.1 Architectures of neural networks
6.1.2 Neural networks input data type
6.2 Types of formal methods applicable
6.2.1 General
6.2.2 Solver
6.2.3 Abstract interpretation
6.2.4 Reachability analysis in deterministic environments
6.2.5 Reachability analysis in non-deterministic environments
6.2.6 Model checking
6.3 Summary
7 Robustness during the life cycle
7.1 General
7.2 During design and development
7.2.1 General
7.2.2 Identifying the recognized features
7.2.3 Checking separability
7.3 During verification and validation
7.3.1 General
7.3.2 Covering parts of the input domain
7.3.3 Measuring perturbation impact
7.4 During deployment
7.5 During operation and monitoring
7.5.1 General
7.5.2 Robustness on a domain of operation
7.5.3 Changes in robustness
Bibliography
Keep me up-to-date
Sign up to receive updates when there are changes to this standard
Related Information
Similar Standards
-
AS/NZS 3802:1997
Data elements and interchange formats - Information interchange - Representation of dates and times
-
AS/NZS 5121:2015
Information technology - Vocabulary - Learning, education and training -
AS/NZS 5813.1:2012
Information technology equipment - Energy performance of computers - Part 1: Methods of measurement of energy performance -
AS/NZS 5813.2:2012
Information technology equipment - Energy performance of computers - Part 2: Minimum energy performance standards (MEPS) for computers
Foreword
Introduction
1 Scope
2 Normative references
3 Terms and definitions
4 Abbreviated terms
5 Robustness assessment
5.1 General
5.2 Notion of domain
5.3 Stability
5.3.1 Stability property
5.3.2 Stability criterion
5.4 Sensitivity
5.4.1 Sensitivity property
5.4.2 Sensitivity criterion
5.5 Relevance
5.5.1 Relevance property
5.5.2 Relevance criterion
5.6 Reachability
5.6.1 Reachability property
5.6.2 Reachability criterion
6 Applicability of formal methods on neural networks
6.1 Types of neural network concerned
6.1.1 Architectures of neural networks
6.1.2 Neural networks input data type
6.2 Types of formal methods applicable
6.2.1 General
6.2.2 Solver
6.2.3 Abstract interpretation
6.2.4 Reachability analysis in deterministic environments
6.2.5 Reachability analysis in non-deterministic environments
6.2.6 Model checking
6.3 Summary
7 Robustness during the life cycle
7.1 General
7.2 During design and development
7.2.1 General
7.2.2 Identifying the recognized features
7.2.3 Checking separability
7.3 During verification and validation
7.3.1 General
7.3.2 Covering parts of the input domain
7.3.3 Measuring perturbation impact
7.4 During deployment
7.5 During operation and monitoring
7.5.1 General
7.5.2 Robustness on a domain of operation
7.5.3 Changes in robustness
Bibliography