Deep neural networks and data for automated driving : robustness, uncertainty quantification, and insights towards safety / Tim Fingscheidt, Hanno Gottschalk, Sebastian Houben, editors

Contributor(s):

Resource type: Ressourcentyp: Buch (Online)Book (Online)Language: English Series: Springer eBook CollectionPublisher: Cham : Springer, [2022]Copyright date: © 2022Description: 1 Online-Ressource (XVIII, 427 Seiten) : IllustrationenISBN:

9783031012334

Subject(s):

Additional physical formats: 9783031012327 | 9783031012341 | 9783031012358 | 9783031034916 | 9783031034909 | 9783031034893 | 9783031034886 | Erscheint auch als: 9783031012327 Druck-Ausgabe | Erscheint auch als: 9783031012341 Druck-Ausgabe | Erscheint auch als: 9783031012358 Druck-Ausgabe | Erscheint auch als: 9783031034916 Druck-Ausgabe | Erscheint auch als: 9783031034909 Druck-Ausgabe | Erscheint auch als: 9783031034893 Druck-Ausgabe | Erscheint auch als: 9783031034886 Druck-AusgabeDOI: DOI: 10.1007/978-3-031-01233-4Online resources:

Summary: 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.Summary: 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.PPN: PPN: 1807341712Package identifier: Produktsigel: ZDB-2-ENG | ZDB-2-SEB | ZDB-2-SOB | ZDB-2-SXE

Holdings ( 0 )
Title notes ( 1 )

No physical items for this record

Open Access