🔥🔥 Don’t Miss Out on Our End of Autumn Sale. If you have any questions, feel free to click the bottom right corner to contact our customer service..

Concat us[email protected]
Shopping Cart

No products in the cart.

🔍
BSI PD CEN/CLC ISO/IEC/TR 24029-1:2023:2024 Edition

BSI PD CEN/CLC ISO/IEC/TR 24029-1:2023:2024 Edition

$167.15

Artificial Intelligence (AI). Assessment of the robustness of neural networks – Overview

Published By Publication Date Number of Pages
BSI 2024 40
PDF Format Searchable Printable Preview Now
Guaranteed Safe Checkout
Category:

If you have any questions, feel free to reach out to our online customer service team by clicking on the bottom right corner. We’re here to assist you 24/7.
Email:[email protected]

This document provides background about existing methods to assess the robustness of neural networks.

PDF Catalog

PDF Pages PDF Title
2 undefined
6 Foreword
7 Introduction
9 1 Scope
2 Normative references
3 Terms and definitions
11 4 Overview of the existing methods to assess the robustness of neural networks
4.1 General
4.1.1 Robustness concept
4.1.2 Typical workflow to assess robustness
14 4.2 Classification of methods
15 5 Statistical methods
5.1 General
16 5.2 Robustness metrics available using statistical methods
5.2.1 General
5.2.2 Examples of performance measures for interpolation
17 5.2.3 Examples of performance measures for classification
21 5.2.4 Other measures
22 5.3 Statistical methods to measure robustness of a neural network
5.3.1 General
5.3.2 Contrastive measures
6 Formal methods
6.1 General
23 6.2 Robustness goal achievable using formal methods
6.2.1 General
6.2.2 Interpolation stability
6.2.3 Maximum stable space for perturbation resistance
24 6.3 Conduct the testing using formal methods
6.3.1 Using uncertainty analysis to prove interpolation stability
6.3.2 Using solver to prove a maximum stable space property
6.3.3 Using optimization techniques to prove a maximum stable space property
25 6.3.4 Using abstract interpretation to prove a maximum stable space property
7 Empirical methods
7.1 General
7.2 Field trials
26 7.3 A posteriori testing
27 7.4 Benchmarking of neural networks
28 Annex A (informative) Data perturbation
33 Annex B (informative) Principle of abstract interpretation
34 Bibliography

Related products

BSI PD CEN/CLC ISO/IEC/TR 24029-1:2023
$167.15