國立虎尾科技大學 |

Deep Neural Networks and Data for Automated Driving = Robustness, Uncertainty Quantification, and Insights Towards Safety /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Deep Neural Networks and Data for Automated Driving/ edited by Tim Fingscheidt, Hanno Gottschalk, Sebastian Houben.
Reminder of title:	Robustness, Uncertainty Quantification, and Insights Towards Safety /
other author:	Fingscheidt, Tim.
Description:	XVIII, 427 p. 117 illus., 103 illus. in color.online resource. :
Contained By:	Springer Nature eBook
Subject:	Automotive engineering. -
Online resource:	https://doi.org/10.1007/978-3-031-01233-4
ISBN:	9783031012334

Deep Neural Networks and Data for Automated Driving = Robustness, Uncertainty Quantification, and Insights Towards Safety /
Deep Neural Networks and Data for Automated DrivingRobustness, Uncertainty Quantification, and Insights Towards Safety /[electronic resource] :edited by Tim Fingscheidt, Hanno Gottschalk, Sebastian Houben. - 1st ed. 2022. - XVIII, 427 p. 117 illus., 103 illus. in color.online resource.

Chapter 1. Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety -- Chapter 2. Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance? -- Chapter 3. Analysis and Comparison of Datasets by Leveraging Data Distributions in Latent Spaces -- Chapter 4. Optimized Data Synthesis for DNN Training and Validation by Sensor Artifact Simulation -- Chapter 5. Improved DNN Robustness by Multi-Task Training With an Auxiliary Self-Supervised Task -- Chapter 6. Improving Transferability of Generated Universal Adversarial Perturbations for Image Classiﬁcation and Segmentation -- Chapter 7. Invertible Neural Networks for Understanding Semantics of Invariances of CNN Representations -- Chapter 8. Conﬁdence Calibration for Object Detection and Segmentation -- Chapter 9. Uncertainty Quantiﬁcation for Object Detection: Output- and Gradient-based Approaches -- Chapter 10. Detecting and Learning the Unknown in Semantic Segmentation -- Chapter 11. Evaluating Mixture-of-Expert Architectures for Network Aggregation -- Chapter 12. Safety Assurance of Machine Learning for Perception Functions -- Chapter 13. A Variational Deep Synthesis Approach for Perception Validation -- Chapter 14. The Good and the Bad: Using Neuron Coverage as a DNN Validation Technique -- Chapter 15. Joint Optimization for DNN Model Compression and Corruption Robustness.

Open Access

This open access book brings together the latest developments from industry and research on automated driving and artificial intelligence. Environment perception for highly automated driving heavily employs deep neural networks, facing many challenges. How much data do we need for training and testing? How to use synthetic data to save labeling costs for training? How do we increase robustness and decrease memory usage? For inevitably poor conditions: How do we know that the network is uncertain about its decisions? Can we understand a bit more about what actually happens inside neural networks? This leads to a very practical problem particularly for DNNs employed in automated driving: What are useful validation techniques and how about safety? This book unites the views from both academia and industry, where computer vision and machine learning meet environment perception for highly automated driving. Naturally, aspects of data, robustness, uncertainty quantification, and, last but not least, safety are at the core of it. This book is unique: In its first part, an extended survey of all the relevant aspects is provided. The second part contains the detailed technical elaboration of the various questions mentioned above.

ISBN: 9783031012334

Standard No.: 10.1007/978-3-031-01233-4doiSubjects--Topical Terms:

1104081
Automotive engineering.

LC Class. No.: TL1-483

Dewey Class. No.: 629.2

Deep Neural Networks and Data for Automated Driving = Robustness, Uncertainty Quantification, and Insights Towards Safety /
LDR:04338nam a22004695i 4500 001 1087527
003 DE-He213
005 20220617133323.0
007 cr nn 008mamaa
008 221228s2022 sz | s |||| 0|eng d
020 $a 9783031012334 $9 978-3-031-01233-4
024 7 $a 10.1007/978-3-031-01233-4 $2 doi
035 $a 978-3-031-01233-4
050 4 $a TL1-483
072 7 $a TRC $2 bicssc
072 7 $a TEC009090 $2 bisacsh
072 7 $a TRC $2 thema
082 0 4 $a 629.2 $2 23
245 1 0 $a Deep Neural Networks and Data for Automated Driving $h [electronic resource] : $b Robustness, Uncertainty Quantification, and Insights Towards Safety / $c edited by Tim Fingscheidt, Hanno Gottschalk, Sebastian Houben.
250 $a 1st ed. 2022.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a XVIII, 427 p. 117 illus., 103 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
505 0 $a Chapter 1. Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety -- Chapter 2. Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance? -- Chapter 3. Analysis and Comparison of Datasets by Leveraging Data Distributions in Latent Spaces -- Chapter 4. Optimized Data Synthesis for DNN Training and Validation by Sensor Artifact Simulation -- Chapter 5. Improved DNN Robustness by Multi-Task Training With an Auxiliary Self-Supervised Task -- Chapter 6. Improving Transferability of Generated Universal Adversarial Perturbations for Image Classiﬁcation and Segmentation -- Chapter 7. Invertible Neural Networks for Understanding Semantics of Invariances of CNN Representations -- Chapter 8. Conﬁdence Calibration for Object Detection and Segmentation -- Chapter 9. Uncertainty Quantiﬁcation for Object Detection: Output- and Gradient-based Approaches -- Chapter 10. Detecting and Learning the Unknown in Semantic Segmentation -- Chapter 11. Evaluating Mixture-of-Expert Architectures for Network Aggregation -- Chapter 12. Safety Assurance of Machine Learning for Perception Functions -- Chapter 13. A Variational Deep Synthesis Approach for Perception Validation -- Chapter 14. The Good and the Bad: Using Neuron Coverage as a DNN Validation Technique -- Chapter 15. Joint Optimization for DNN Model Compression and Corruption Robustness.
506 0 $a Open Access
520 $a This open access book brings together the latest developments from industry and research on automated driving and artificial intelligence. Environment perception for highly automated driving heavily employs deep neural networks, facing many challenges. How much data do we need for training and testing? How to use synthetic data to save labeling costs for training? How do we increase robustness and decrease memory usage? For inevitably poor conditions: How do we know that the network is uncertain about its decisions? Can we understand a bit more about what actually happens inside neural networks? This leads to a very practical problem particularly for DNNs employed in automated driving: What are useful validation techniques and how about safety? This book unites the views from both academia and industry, where computer vision and machine learning meet environment perception for highly automated driving. Naturally, aspects of data, robustness, uncertainty quantification, and, last but not least, safety are at the core of it. This book is unique: In its first part, an extended survey of all the relevant aspects is provided. The second part contains the detailed technical elaboration of the various questions mentioned above.
650 0 $a Automotive engineering. $3 1104081
650 0 $a Neural networks (Computer science) . $3 1253765
650 0 $a Computer vision. $3 561800
650 0 $a Engineering—Data processing. $3 1297966
650 1 4 $a Automotive Engineering. $3 683772
650 2 4 $a Mathematical Models of Cognitive Processes and Neural Networks. $3 884110
650 2 4 $a Computer Vision. $3 1127422
650 2 4 $a Data Engineering. $3 1226308
700 1 $a Fingscheidt, Tim. $e editor. $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1394558
700 1 $a Gottschalk, Hanno. $e editor. $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1394559
700 1 $a Houben, Sebastian. $e editor. $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1394560
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783031012327
776 0 8 $i Printed edition: $z 9783031012341
776 0 8 $i Printed edition: $z 9783031012358
776 0 8 $i Printed edition: $z 9783031034916
776 0 8 $i Printed edition: $z 9783031034909
776 0 8 $i Printed edition: $z 9783031034893
776 0 8 $i Printed edition: $z 9783031034886
856 4 0 $u https://doi.org/10.1007/978-3-031-01233-4
912 $a ZDB-2-ENG
912 $a ZDB-2-SXE
912 $a ZDB-2-SOB
950 $a Engineering (SpringerNature-11647)
950 $a Engineering (R0) (SpringerNature-43712)