Refine
H-BRS Bibliography
- yes (187) (remove)
Departments, institutes and facilities
- Fachbereich Angewandte Naturwissenschaften (56)
- Fachbereich Wirtschaftswissenschaften (33)
- Fachbereich Informatik (29)
- Institut für funktionale Gen-Analytik (IFGA) (21)
- Fachbereich Ingenieurwissenschaften und Kommunikation (19)
- Fachbereich Sozialpolitik und Soziale Sicherung (18)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (16)
- Sprachenzentrum (10)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (7)
- Institut für Verbraucherinformatik (IVI) (6)
Document Type
- Part of a Book (187) (remove)
Year of publication
Language
- English (187) (remove)
Keywords
- GC/MS (5)
- Polymers (4)
- Lignin (3)
- Mesenchymal stem cells (3)
- Pyrolysis (3)
- Regenerative medicine (3)
- Scaffolds (3)
- Analytical pyrolysis (2)
- Antimicrobial activity (2)
- Antioxidant activity (2)
Social policy research on the ageing workforce from the perspective of employees and employers
(2024)
The Peren Theorem
(2024)
The Peren-Clement Index
(2024)
Network Analysis Method
(2024)
Dynamic Programming
(2024)
Heuristic Methods
(2024)
Sequencing Problems
(2024)
Queueing Theory
(2024)
Linear Optimization
(2024)
The Decision Tree Procedure
(2024)
The UN Declaration on the Right to Development (UNDRTD) adopted in 1986 and the 2030 Agenda for Sustainable Development adopted in 2015 share a universal concept of development that refers both to individual and collective dimensions of prosperity and thus includes the rights of future generations.2 They thus offer a definition of the relationship between development and human rights that is very relevant for the 21st century. The core norm of the UNDRTD has been defined later as “the right of peoples and individuals to the constant improvement of their wellbeing and to a national and global enabling environment conducive to just, equitable, participatory and human-centred development respectful of all human rights”3.
Deployment of modern data-driven machine learning methods, most often realized by deep neural networks (DNNs), in safety-critical applications such as health care, industrial plant control, or autonomous driving is highly challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability and implausible predictions to directed attacks by means of malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from so-called safety concerns, properties that preclude their deployment as no argument or experimental setup can help to assess the remaining risk. In recent years, an abundance of state-of-the-art techniques aiming to address these safety concerns has emerged. This chapter provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our work addresses machine learning experts and safety engineers alike: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern machine learning methods. We hope that this contribution fuels discussions on desiderata for machine learning systems and strategies on how to help to advance existing approaches accordingly.
From Conclusion to Coda
(2022)