This paper proposes a forward adaptive transfer learning method, referred tp as forward adaptive transfer learning for Gaussian process regression, which allows robots to leverage previously learned Gaussian process regression models and use them as sources of information in new learning tasks. This is especially valuable when limited training data are available for the new target task. Forward adaptive transfer learning for Gaussian process regression decouples the kernel and hyperparameter selection for the target task from those of the source task, providing an inference framework that is desirable when dealing with real-world dynamic environments. Finally, because the source task has been learned a priori, the computational complexity of forward adaptive transfer learning for Gaussian process regression is lower as compared to other semiparametric Gaussian process approaches using transfer kernels.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Forward Adaptive Transfer of Gaussian Process Regression


    Contributors:

    Published in:

    Publication date :

    2017-04-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Personalized Adaptive Cruise Control via Gaussian Process Regression

    Wang, Yanbing / Wang, Ziran / Han, Kyungtae et al. | IEEE | 2021


    Thermal matching using Gaussian process regression

    Pearce, Robert / Ireland, Peter / Romero, Eduardo | SAGE Publications | 2020

    Free access


    Vehicle consumption estimation via calibrated Gaussian Process regression

    Randon, Mathieu / Quost, Benjamin / Boudaoud, Nassim et al. | IEEE | 2022


    Multiresolution partitioned Gaussian process regression for terrain estimation

    Zhang, Clark / Ono, Masahiro / Lanka, Ravi | IEEE | 2018