Paper on adaptive sampling for multi-task Gaussian processes published in JMS

Our paper titled “Adaptive sampling design for multi-task learning of Gaussian processes in manufacturing” has been published in the Journal of Manufacturing Systems. The paper was co-authored by Manan Mehta and Prof. Chenhui Shao.

Multi-task learning (MTL) is a machine learning technique used to enhance learning performance in similar-but-not-identical tasks. However, the accuracy of MTL is largely a function of the sampling design used for training points. Our work formulates an intelligent and sequential sampling method to maximize information acquisition from each added training point. We demonstrate the effectiveness of our method using a surface-shape prediction case study and show that combining MTL with intelligent sampling yields state-of-the-art results.

Read the full paper here.