國立高雄大學圖資館 |

登入

回首頁

Deep neural networks and data for automated drivingrobustness, uncertainty quantification, and insights towards safety /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep neural networks and data for automated drivingedited by Tim Fingscheidt, Hanno Gottschalk, Sebastian Houben.
其他題名:	robustness, uncertainty quantification, and insights towards safety /
其他作者:	Fingscheidt, Tim.
出版者:	Cham :Springer International Publishing :2022.
面頁冊數:	xviii, 427 p. :ill. (some col.), digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Vehicular ad hoc networks (Computer networks)
電子資源:	https://doi.org/10.1007/978-3-031-01233-4
ISBN:	9783031012334$q(electronic bk.)

Deep neural networks and data for automated drivingrobustness, 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. - Cham :Springer International Publishing :2022. - xviii, 427 p. :ill. (some col.), digital ;24 cm.

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$q(electronic bk.)

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

383232
Vehicular ad hoc networks (Computer networks)

LC Class. No.: TL152.8 / .D44 2022

Dewey Class. No.: 629.046

Deep neural networks and data for automated drivingrobustness, uncertainty quantification, and insights towards safety /
LDR:03819nmm a2200349 a 4500 001 625816
003 DE-He213
005 20220617133323.0
006 m d
007 cr nn 008maaau
008 230109s2022 sz s 0 eng d
020 $a 9783031012334$q(electronic bk.)
020 $a 9783031012327$q(paper)
024 7 $a 10.1007/978-3-031-01233-4 $2 doi
035 $a 978-3-031-01233-4
040 $a GP $c GP
041 0 $a eng
050 4 $a TL152.8 $b .D44 2022
072 7 $a TRC $2 bicssc
072 7 $a TEC009090 $2 bisacsh
072 7 $a TRC $2 thema
082 0 4 $a 629.046 $2 23
090 $a TL152.8 $b .D311 2022
245 0 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.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a xviii, 427 p. : $b ill. (some col.), digital ; $c 24 cm.
338 $a online resource $b cr $2 rdacarrier
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 $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 Vehicular ad hoc networks (Computer networks) $3 383232
650 0 $a Neural networks (Computer science) $3 181982
650 1 4 $a Automotive Engineering. $3 308930
650 2 4 $a Mathematical Models of Cognitive Processes and Neural Networks. $3 567118
650 2 4 $a Computer Vision. $3 913138
650 2 4 $a Data Engineering. $3 839346
650 0 $a Automated vehicles. $3 849313
700 1 $a Fingscheidt, Tim. $3 929389
700 1 $a Gottschalk, Hanno. $3 929390
700 1 $a Houben, Sebastian. $3 929391
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-031-01233-4
950 $a Engineering (SpringerNature-11647)