Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Introduction to “Systems Engineering and Artificial Intelligence” and the Chapters Read chapter Read first chapter

2021 | OriginalPaper | Chapter

19. Toward Safe Decision-Making via Uncertainty Quantification in Machine Learning

Authors : Adam D. Cobb, Brian Jalaian, Nathaniel D. Bastian, Stephen Russell

Published in: Systems Engineering and Artificial Intelligence

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The automation of safety-critical systems is becoming increasingly prevalent as machine learning approaches become more sophisticated and capable. However, approaches that are safe to use in critical systems must account for uncertainty. Most real-world applications currently use deterministic machine learning techniques that cannot incorporate uncertainty. In order to place systems in critical infrastructure, we must be able to understand and interpret how machines make decisions. This need is so that they can provide support for human decision-making, as well as the potential to operate autonomously. As such, we highlight the importance of incorporating uncertainty into the decision-making process and present the advantages of Bayesian decision theory. We showcase an example of classifying vehicles from their acoustic recordings, where certain classes have significantly higher threat levels. We show how carefully adopting the Bayesian paradigm not only leads to safer decisions, but also provides a clear distinction between the roles of the machine learning expert and the domain expert.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Shifting Paradigms in Verification and Validation of AI-Enabled Systems: A Systems-Theoretic Perspective
next chapter Engineering Context from the Ground Up
Footnotes
1
Neural network models can take on the form of many different types of architectures and we refer to Goodfellow et al. (2016) for more details.
 
2
In Bayesian decision theory, the cost is often referred to as the loss. However, to prevent confusion with the use of the term ‘loss’ for neural networks, we use cost here.
 
3
Audio was recorded at a sampling rate of 1025.641 Hz.
 
4
Unsafe events should be rare if systems are built well!
 
5
Based on the following parameters: OS: Ubuntu 18.04.5; CPU: Intel i7-9750H; GPU: GeForce RTX 2080 with Max-Q; Python: 3.8.3.
 
6
The reduction in quality of the approximation is not evident here.
 
Literature
Bastian, N. D., Lunday, B. J., Fisher, C. B., & Hall, A. O. (2020). Models and methods for workforce planning under uncertainty: Optimizing us army cyber branch readiness and manning. Omega, 92,
Bayes, T. (1763). LII. An essay towards solving a problem in the doctrine of chances. By the late Rev. Mr. Bayes, FRS communicated by Mr. Price, in a letter to John Canton, AMFR S. Philosophical transactions of the Royal Society of London, (53), 370–418.
Berger, J. O. (1985). Statistical Decision Theory and Bayesian Analysis. Springer Science & Business Media.
Blundell, C., Cornebise, J., Kavukcuoglu, K., & Wierstra, D. (2015). Weight uncertainty in neural networks. In Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37, pp. 1613–1622. JMLR. org.
Cobb, A. D. (2020). The practicalities of scaling Bayesian neural networks to real-world applications. Ph.D. thesis, University of Oxford.
Cobb, A. D., & Jalaian, B. (2020). Scaling hamiltonian monte carlo inference for Bayesian neural networks with symmetric splitting. arXiv:​2010.​06772.
Cobb, A. D., Roberts, S. J., & Gal, Y. (2018). Loss-calibrated approximate inference in Bayesian neural networks. In Theory of Deep Learning Workshop, ICML.
Ekin, T., Kocadagli, O., Bastian, N. D., Fulton, L. V., & Griffin, P. M. (2016). Fuzzy decision making in health systems: A resource allocation model. EURO Journal on Decision Processes, 4(3–4), 245–267.CrossRef
Gal Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning, pp. 1050–1059.
Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A., & Rubin, D. B. (2013). Bayesian data analysis. CRC Press.
Graves, A. (2011). Practical variational inference for neural networks. In Advances in Neural Information Processing Systems, pp. 2348–2356.
Hendler, J., & Mulvehill, A. M. (2016). Social machines: The coming collision of artificial intelligence, social networking, and humanity. Apress
Hoffman, M. D., Blei, D. M., Wang, C., & Paisley, J. (2013). Stochastic variational inference. The Journal of Machine Learning Research, 14(1), 1303–1347.MathSciNetMATH
Hurd, H., & Pham, T. (2002). Target association using harmonic frequency tracks. In Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002.(IEEE Cat. No. 02EX5997) (Vol. 2, pp. 860–864). IEEE.
Kiskin, I., Cobb, A. D., Wang, L., & Roberts, S. (2020a). Humbug zooniverse: A crowd-sourced acoustic mosquito dataset. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 916–920). IEEE.
Kiskin, I., Zilli, D., Li, Y., Sinka, M., Willis, K., & Roberts, S. (2020b). Bioacoustic detection with wavelet-conditioned convolutional neural networks. Neural Computing and Applications, 32(4), 915–927.
Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017). Self-normalizing neural networks. In Advances in neural information processing systems (pp. 971–980).
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (pp. 1097–1105).
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.CrossRef
Leibig, C., Allken, V., Ayhan, M. S., Berens, P., & Wahl, S. (2017). Leveraging uncertainty information from deep neural networks for disease detection. Scientific reports, 7(1), 17816.CrossRef
Leqi, L., Prasad, A., & Ravikumar, P. K. (2019). On human-aligned risk minimization. In Advances in Neural Information Processing Systems (pp. 15055–15064).
Lohani, M., Stokes, C., Dashan, N., McCoy, M., Bailey, C. A. & Rivers, S. E. (2017).Rivers. A framework for human-agent social systems: The role of non-technical factors in operation success. In Advances in human factors in robots and unmanned systems (pp. 137–148). Springer.
Neal, R. M. (1995). Bayesian learning for neural networks. Ph.D. thesis, University of Toronto.
Nilsson, N. J. (2014). Principles of artificial intelligence. Morgan Kaufmann.
Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., & Lerer, A. (2017). Automatic differentiation in PyTorch. In NIPS Autodiff Workshop.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., & Vanderplas, J. (2011). Scikit-learn: Machine learning in python. Journal of Machine Learning Research, 12(85), 2825–2830. http://​jmlr.​org/​papers/​v12/​pedregosa11a.​html.
Polymenakos, K., Abate, A., & Roberts, S. (2019). Safe policy search using gaussian process models. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (pp. 1565–1573).
Robert, C., & Casella, G. (2013). Monte carlo statistical methods. Springer Science & Business Media.
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Parallel distributed processing: Explorations in the microstructure of cognition, chapter Learning Internal Representations by Error Propagation, (Vol. 1, pp. 318–362). Cambridge, MA, USA: MIT Press.
Russell, S., Moskowitz, I. S., & Raglin, A. (2017). Human information interaction, artificial intelligence, and errors. In Autonomy and Artificial Intelligence: A Threat or Savior? (pp. 71–101). Springer.
Spears, T., Zohren, S., & Roberts, S. (2020). Investment sizing with deep learning prediction uncertainties for high-frequency eurodollar futures trading. SSRN 3664497.
Taskin, S., & Lodree, E. (2016). A bayesian decision model with hurricane forecast up-dates for emergency supplies inventory management. In Operational Research for Emergency Planning in Healthcare (Vol. 1, pp. 330–352) Springer.
Welling, M., & Teh, Y. W. (2011). Bayesian learning via stochastic gradient Langevin dynamics. In Proceedings of the 28th International Conference on Machine Learning (ICML-11) (pp. 681–688).
Williams, C. K., & Rasmussen, C. E. (2006). Gaussian processes for machine learning (Vol. 2). MA: MIT press Cambridge.MATH
Metadata
Title
Toward Safe Decision-Making via Uncertainty Quantification in Machine Learning
Authors
Adam D. Cobb
Brian Jalaian
Nathaniel D. Bastian
Stephen Russell
Copyright Year
2021
Book
Systems Engineering and Artificial Intelligence

Print ISBN: 978-3-030-77282-6

Electronic ISBN: 978-3-030-77283-3

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-77283-3_19

Premium Partner

    Image Credits