This paper presents a probabilistic framework to obtain both reliable and fast uncertainty estimates for predictions with Deep Neural Networks (DNNs). Our main contribution is a practical and principled combination of DNNs with sparse Gaussian Processes (GPs). We prove theoretically that DNNs can be seen as a special case of sparse GPs, namely mixtures of GP experts (MoE-GP), and we devise a learning algorithm that brings the derived theory into practice. In experiments from two different robotic tasks – inverse dynamics of a manipulator and object detection on a micro-aerial vehicle (MAV) – we show the effectiveness of our approach in terms of predictive uncertainty, proved scalability, and runtime efficiency on a Jetson TX2. We thus argue that our approach can pave the way towards reliable and fast robot learning systems with uncertainty wareness.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes


    Beteiligte:

    Kongress:



    Erscheinungsdatum :

    08.11.2021


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Estimating Model Uncertainty of Neural Networks in Sparse Information Form

    Lee, Jongseok / Humt, Matthias / Feng, Jianxiang et al. | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2020

    Freier Zugriff

    Scenario Uncertainty Modeling for Predictive Maintenance with Recurrent Neural Adaptive Processes (RNAPs)

    Yu, Wenbo / Zhao, Xijian / Sun, Yong et al. | British Library Conference Proceedings | 2021


    Scenario Uncertainty Modeling for Predictive Maintenance with Recurrent Neural Adaptive Processes (RNAPs)

    Yu, Wenbo / Zhao, Xijian / Li, Xuejiao et al. | SAE Technical Papers | 2021


    Modeling trust with uncertainty for open networks

    Rui, H. / Jianwei, N. / Jianping, H. | British Library Online Contents | 2004