Improved active output selection strategy for noisy environments

TL;DR

This paper introduces an improved active output selection strategy for model calibration in noisy environments, leveraging noise estimates in Gaussian processes to reduce measurement needs by at least 10% in toy examples.

Contribution

The paper proposes a novel active output selection method that incorporates noise estimates, enhancing calibration efficiency over existing strategies.

Findings

Performance is equal or better than existing strategies in toy examples.

At least 10% reduction in measurements needed in best case scenarios.

Validated on three different toy examples.

Abstract

The test bench time needed for model-based calibration can be reduced with active learning methods for test design. This paper presents an improved strategy for active output selection. This is the task of learning multiple models in the same input dimensions and suits the needs of calibration tasks. Compared to an existing strategy, we take into account the noise estimate, which is inherent to Gaussian processes. The method is validated on three different toy examples. The performance compared to the existing best strategy is the same or better in each example. In a best case scenario, the new strategy needs at least 10% less measurements compared to all other active or passive strategies. Further efforts will evaluate the strategy on a real-world application. Moreover, the implementation of more sophisticated active-learning strategies for the query placement will be realized.