Cargando…

Guidance for the verification and validation of neural networks

Guidance for the Verification and Validation of Neural Networks is a supplement to the IEEE Standard for Software Verification and Validation, IEEE Std 1012-1998. Born out of a need by the National Aeronautics and Space Administration's safety- and mission-critical research, this book compiles...

Descripción completa

Detalles Bibliográficos
Autores principales: Pullum, L, Taylor, B, Darrah, M
Lenguaje:eng
Publicado: Wiley-IEEE Press 2007
Materias:
Acceso en línea:http://cds.cern.ch/record/2116410
_version_ 1780949208912625664
author Pullum, L
Taylor, B
Darrah, M
author_facet Pullum, L
Taylor, B
Darrah, M
author_sort Pullum, L
collection CERN
description Guidance for the Verification and Validation of Neural Networks is a supplement to the IEEE Standard for Software Verification and Validation, IEEE Std 1012-1998. Born out of a need by the National Aeronautics and Space Administration's safety- and mission-critical research, this book compiles over five years of applied research and development efforts. It is intended to assist the performance of verification and validation (V&V) activities on adaptive software systems, with emphasis given to neural network systems. The book discusses some of the difficulties with trying to assure adaptive systems in general, presents techniques and advice for the V&V practitioner confronted with such a task, and based on a neural network case study, identifies specific tasking and recommendations for the V&V of neural network systems.
id cern-2116410
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2007
publisher Wiley-IEEE Press
record_format invenio
spelling cern-21164102021-04-21T19:56:47Zhttp://cds.cern.ch/record/2116410engPullum, LTaylor, BDarrah, MGuidance for the verification and validation of neural networksEngineeringGuidance for the Verification and Validation of Neural Networks is a supplement to the IEEE Standard for Software Verification and Validation, IEEE Std 1012-1998. Born out of a need by the National Aeronautics and Space Administration's safety- and mission-critical research, this book compiles over five years of applied research and development efforts. It is intended to assist the performance of verification and validation (V&V) activities on adaptive software systems, with emphasis given to neural network systems. The book discusses some of the difficulties with trying to assure adaptive systems in general, presents techniques and advice for the V&V practitioner confronted with such a task, and based on a neural network case study, identifies specific tasking and recommendations for the V&V of neural network systems.Wiley-IEEE Pressoai:cds.cern.ch:21164102007
spellingShingle Engineering
Pullum, L
Taylor, B
Darrah, M
Guidance for the verification and validation of neural networks
title Guidance for the verification and validation of neural networks
title_full Guidance for the verification and validation of neural networks
title_fullStr Guidance for the verification and validation of neural networks
title_full_unstemmed Guidance for the verification and validation of neural networks
title_short Guidance for the verification and validation of neural networks
title_sort guidance for the verification and validation of neural networks
topic Engineering
url http://cds.cern.ch/record/2116410
work_keys_str_mv AT pulluml guidancefortheverificationandvalidationofneuralnetworks
AT taylorb guidancefortheverificationandvalidationofneuralnetworks
AT darrahm guidancefortheverificationandvalidationofneuralnetworks