Decision making under uncertainty with convolutional deep Gaussian processes

Jain, D and Anumasa, S and Srijith, P K (2020) Decision making under uncertainty with convolutional deep Gaussian processes. In: ACM India Joint 7th ACM IKDD Conference on Data Science and 25th International Conference on Management of Data, CoDS-COMAD, 5-7 January 2020, Hyderabad, India.

Full text not available from this repository. (Request a copy)


Deep learning models such as convolutional neural networks have brought advances in computer vision and were found to surpass human accuracy in computer vision problems. This has resulted in their use in many safety critical applications such as autonomous driving and healthcare, where decision making under uncertainty is crucial. However, deep learning models are vulnerable to out of sample and adversarial examples and they can be very risky to use in safety critical applications. Deep Gaussian process provide a Bayesian non-parametric approach to deep learning and are capable of modelling the uncertainty in data and model. In this paper, we show the uncertainty quantification capabilities of Convolutional deep Gaussian processes for computer vision problems. We show that convolutional deep Gaussian processes provide better uncertainty estimates for various settings such as out-of-distribution samples, adversarial attacks and uncertainty calibration experiments. They are found to be more robust than convolutional neural networks, Bayesian convolutional neural networks and deep Gaussian processes for image classification.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Bayesian learning, Deep learning, Gaussian processes, Uncertainty quantification, Indexed in Scopus
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: Team Library
Date Deposited: 10 Feb 2020 07:41
Last Modified: 10 Feb 2020 07:41
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 7423 Statistics for this ePrint Item