{"id":465146,"date":"2024-10-20T10:38:58","date_gmt":"2024-10-20T10:38:58","guid":{"rendered":"https:\/\/pdfstandards.shop\/product\/uncategorized\/bsi-pd-cen-clc-iso-iec-tr-24029-12023-2\/"},"modified":"2024-10-26T19:39:16","modified_gmt":"2024-10-26T19:39:16","slug":"bsi-pd-cen-clc-iso-iec-tr-24029-12023-2","status":"publish","type":"product","link":"https:\/\/pdfstandards.shop\/product\/publishers\/bsi\/bsi-pd-cen-clc-iso-iec-tr-24029-12023-2\/","title":{"rendered":"BSI PD CEN\/CLC ISO\/IEC\/TR 24029-1:2023"},"content":{"rendered":"
This document provides background about existing methods to assess the robustness of neural networks.<\/p>\n
PDF Pages<\/th>\n | PDF Title<\/th>\n<\/tr>\n | ||||||
---|---|---|---|---|---|---|---|
2<\/td>\n | undefined <\/td>\n<\/tr>\n | ||||||
6<\/td>\n | Foreword <\/td>\n<\/tr>\n | ||||||
7<\/td>\n | Introduction <\/td>\n<\/tr>\n | ||||||
9<\/td>\n | 1 Scope 2 Normative references 3 Terms and definitions <\/td>\n<\/tr>\n | ||||||
11<\/td>\n | 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 <\/td>\n<\/tr>\n | ||||||
14<\/td>\n | 4.2 Classification of methods <\/td>\n<\/tr>\n | ||||||
15<\/td>\n | 5 Statistical methods 5.1 General <\/td>\n<\/tr>\n | ||||||
16<\/td>\n | 5.2 Robustness metrics available using statistical methods 5.2.1 General 5.2.2 Examples of performance measures for interpolation <\/td>\n<\/tr>\n | ||||||
17<\/td>\n | 5.2.3 Examples of performance measures for classification <\/td>\n<\/tr>\n | ||||||
21<\/td>\n | 5.2.4 Other measures <\/td>\n<\/tr>\n | ||||||
22<\/td>\n | 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 <\/td>\n<\/tr>\n | ||||||
23<\/td>\n | 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 <\/td>\n<\/tr>\n | ||||||
24<\/td>\n | 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 <\/td>\n<\/tr>\n | ||||||
25<\/td>\n | 6.3.4 Using abstract interpretation to prove a maximum stable space property 7 Empirical methods 7.1 General 7.2 Field trials <\/td>\n<\/tr>\n | ||||||
26<\/td>\n | 7.3 A posteriori testing <\/td>\n<\/tr>\n | ||||||
27<\/td>\n | 7.4 Benchmarking of neural networks <\/td>\n<\/tr>\n | ||||||
28<\/td>\n | Annex A (informative) Data perturbation <\/td>\n<\/tr>\n | ||||||
33<\/td>\n | Annex B (informative) Principle of abstract interpretation <\/td>\n<\/tr>\n | ||||||
34<\/td>\n | Bibliography <\/td>\n<\/tr>\n<\/table>\n","protected":false},"excerpt":{"rendered":" Artificial Intelligence (AI). Assessment of the robustness of neural networks – Overview<\/b><\/p>\n |