Informējam, ka Sistēma pielāgota darbam ar interneta pārlūkprogrammu Internet Explorer (8. un jaunākām versijām) un Mozilla Firefox (3.6 un jaunākām versijām).
Izmantojot citu interneta pārlūkprogrammu, brīdinām, ka Sistēmas funkcionalitāte var tikt traucēta.
This document provides requirements and guidance on the application of the ISO/IEC/IEEE 29119 series and ISO/IEC 20246 to the testing of machine learning (ML) software and ML systems. This document requires a risk-based approach to testing, and uses generic risks associated with ML systems, and their development and maintenance, to identify suitable treatments in the form of various test approaches (including test levels, test practices, test types, static testing, and test design techniques and measures). When these test approaches and reviews are already specified in the ISO/IEC/IEEE 29119 series or ISO/IEC 20246, this document provides additional detail and describes their application in the context of ML.
This document does not cover the testing of adaptive ML systems that can change their functionality once operational, such as reinforcement learning systems and other self-learning systems.
Reģistrācijas numurs (WIID)
88853
Darbības sfēra
This document provides requirements and guidance on the application of the ISO/IEC/IEEE 29119 series and ISO/IEC 20246 to the testing of machine learning (ML) software and ML systems. This document requires a risk-based approach to testing, and uses generic risks associated with ML systems, and their development and maintenance, to identify suitable treatments in the form of various test approaches (including test levels, test practices, test types, static testing, and test design techniques and measures). When these test approaches and reviews are already specified in the ISO/IEC/IEEE 29119 series or ISO/IEC 20246, this document provides additional detail and describes their application in the context of ML.
This document does not cover the testing of adaptive ML systems that can change their functionality once operational, such as reinforcement learning systems and other self-learning systems.
