Muutke küpsiste eelistusi

Guidance for the Verification and Validation of Neural Networks [Pehme köide]

, , , , ,
  • Formaat: Paperback / softback, 134 pages, kõrgus x laius x paksus: 252x179x10 mm, kaal: 268 g, Illustrations, Contains 1 Digital online
  • Sari: Emerging Technologies
  • Ilmumisaeg: 04-Apr-2007
  • Kirjastus: Wiley-Blackwell
  • ISBN-10: 047008457X
  • ISBN-13: 9780470084571
Teised raamatud teemal:
  • Pehme köide
  • Hind: 135,48 €*
  • * saadame teile pakkumise kasutatud raamatule, mille hind võib erineda kodulehel olevast hinnast
  • See raamat on trükist otsas, kuid me saadame teile pakkumise kasutatud raamatule.
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Lisa soovinimekirja
  • Raamatukogudele
Guidance for the Verification and Validation of Neural NetworksSuurem pilt
  • Formaat: Paperback / softback, 134 pages, kõrgus x laius x paksus: 252x179x10 mm, kaal: 268 g, Illustrations, Contains 1 Digital online
  • Sari: Emerging Technologies
  • Ilmumisaeg: 04-Apr-2007
  • Kirjastus: Wiley-Blackwell
  • ISBN-10: 047008457X
  • ISBN-13: 9780470084571
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780470084571.html
Märksõnad:
At the US National Aeronautics and Space Administration adaptive software--which can change behavior, function, internal parameters, or realization while in operation--has moved from the experimental to the operational stage. But the processes for verifying conventional software--making sure it is being built right--and validating it--making sure it is solving the correct problem--were not adequate for the new slippery kind, so the agency commissioned a research project to come up with guidelines, which are presented here. Annotation ©2007 Book News, Inc., Portland, OR (booknews.com)

This book provides guidance on the verification and validation of neural networks/adaptive systems. Considering every process, activity, and task in the lifecycle, it supplies methods and techniques that will help the developer or V&V practitioner be confident that they are supplying an adaptive/neural network system that will perform as intended. Additionally, it is structured to be used as a cross-reference to the IEEE 1012 standard.
Preface.
Acknowledgements.
1 Overview.
1.1 Definitions and Conventions.
1.2 Organization of the Book.
2 Areas of Consideration for Adaptive Systems.
2.1 Safety-Critical Adaptive System Example and Experience.
2.2 Hazard Analysis.
2.3 Requirements for Adaptive Systems.
2.4 Rule Extraction.
2.5 Modified Life Cycle for Developing Neural Networks.
2.6 Operational Monitors.
2.7 Testing Considerations.
2.8 Training Set Analysis.
2.9 Stability Analysis
2.10 Configuration Management of Neural Network Training and Design.
2.11 Simulation of Adaptive Systems.
2.12 Neural Network Visualization.
2.13 Adaptive System and Neural Network Selection.
3 Verification and Validation of Neural Networks—Guidance.
3.1 Process: Management.
3.2 Process: Acquisition.
3.3 Process: Supply.
3.4 Process: Development.
3.5 Process: Operation.
3.6 Process: Maintenance.
4 Recent Changes to IEEE Std 1012.
Appendix A: References.
Appendix B: Acronyms.
Appendix C: Definitions.


Dr. Laura L. Pullum is a Principal Research Scientist and Technical Director at Lockheed Martin in Eagan, MN. Her areas of research and development include software and system dependability, verification and validation, adaptive systems, and automated reasoning. Brian J. Taylor served as a Principal Member Research Staff for the Institute for Scientific Research, working with a research team on the development, implementation, and flight qualification of Intelligent Flight Control Systems. He is currently a PhD candidate. Dr. Marjorie A. Darrah is a Principal Scientist for the West Virginia High Technology Consortium Foundation. Her areas of research and development include virtual reality, education, data mining, software verification and validation, algorithm development, and neural networks.