000			04357nam a22004935i 4500
001			978-0-387-29485-8
003			DE-He213
005			20250710083944.0
007			cr nn 008mamaa
008			100301s2006 xxu| s |||| 0|eng d
020			_a9780387294858 _a99780387294858
024	7		_a10.1007/0-387-29485-6 _2doi
082	0	4	_a004.6 _223
100	1		_aTaylor, Brian J. _eauthor.
245	1	0	_aMethods and Procedures for the Verification and Validation of Artificial Neural Networks _h[recurso electrónico] / _cby Brian J. Taylor.
264		1	_aBoston, MA : _bSpringer US, _c2006.
300			_aXI, 277 p. _bonline resource.
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_arecurso en línea _bcr _2rdacarrier
347			_atext file _bPDF _2rda
505	0		_aBackground of the Verification and Validation of Neural Networks -- Augmentation of Current Verification and Validation Practices -- Risk and Hazard Analysis for Neural Network Systems -- Validation of Neural Networks Via Taxonomic Evaluation -- Stability Properties of Neural Networks -- Neural Network Verification -- Neural Network Visualization Techniques -- Rule Extraction as a Formal Method -- Automated Test Generation for Testing Neural Network Systems -- Run-Time Assessment of Neural Network Control Systems.
520			_aArtificial neural networks are a form of artificial intelligence that have the capability of learning, growing, and adapting with dynamic environments. With the ability to learn and adapt, artificial neural networks introduce new potential solutions and approaches to some of the more challenging problems that the United States faces as it pursues the vision of space exploration and develops other system applications that must change and adapt after deployment. Neural networks are members of a class of software that have the potential to enable intelligent computational systems capable of simulating characteristics of biological thinking and learning. Currently no standards exist to verify and validate neural network-based systems. NASA Independent Verification and Validation Facility has contracted the Institute for Scientific Research, Inc. to perform research on this topic and develop a comprehensive guide to performing V&V on adaptive systems, with emphasis on neural networks used in safety-critical or mission-critical applications. Methods and Procedures for the Verification and Validation of Artificial Neural Networks is the culmination of the first steps in that research. This volume introduces some of the more promising methods and techniques used for the verification and validation (V&V) of neural networks and adaptive systems. A comprehensive guide to performing V&V on neural network systems, aligned with the IEEE Standard for Software Verification and Validation, will follow this book. The NASA IV&V and the Institute for Scientific Research, Inc. are working to be at the forefront of software safety and assurance for neural network and adaptive systems. Methods and Procedures for the Verification and Validation of Artificial Neural Networks is structured for research scientists and V&V practitioners in industry to assure neural network software systems for future NASA missions and other applications. This book is also suitable for graduate-level students in computer science and computer engineering.
650		0	_aCOMPUTER SCIENCE.
650		0	_aCOMPUTER NETWORK ARCHITECTURES.
650		0	_aCOMPUTER COMMUNICATION NETWORKS.
650		0	_aARTIFICIAL INTELLIGENCE.
650		0	_aCOMPUTER VISION.
650		0	_aOPTICAL PATTERN RECOGNITION.
650	1	4	_aCOMPUTER SCIENCE.
650	2	4	_aCOMPUTER COMMUNICATION NETWORKS.
650	2	4	_aARTIFICIAL INTELLIGENCE (INCL. ROBOTICS).
650	2	4	_aUSER INTERFACES AND HUMAN COMPUTER INTERACTION.
650	2	4	_aCOMPUTER SYSTEMS ORGANIZATION AND COMMUNICATION NETWORKS.
650	2	4	_aCOMPUTER IMAGING, VISION, PATTERN RECOGNITION AND GRAPHICS.
650	2	4	_aPATTERN RECOGNITION.
710	2		_aSpringerLink (Online service)
773	0		_tSpringer eBooks
776	0	8	_iPrinted edition: _z9780387282886
856	4	0	_uhttp://dx.doi.org/10.1007/0-387-29485-6 _zVer el texto completo en las instalaciones del CICY
912			_aZDB-2-SCS
942			_2ddc _cER
999			_c56963 _d56963