Adaptiveness and consistency of expert based learning algorithms selecting reactions to human movements

Young, Carol; Khan, Ayesha; Zhang, Fumin

doi:10.23919/acc.2017.7963170

Cited by 2 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latter DWM, 22 addictive expert ensembles (or AddExp), 36 and horse racing ensembles (or HRE) 3 algorithms are all modified versions of WMA and Winnow. Another algorithm we will analyze in this article is the multiple expert algorithm (MEA), which is an extended version of the dual expert algorithm (DEA) published in our previous work 12 . We have already analyzed the adaptiveness and consistency of DEA and compared it with two experts WMA and Winnow.…”

Section: Ensemble Learning Algorithmsmentioning

confidence: 99%

“…Main Contributions : Our previous work introduced two performance metrics, called consistency and adaptiveness, for online ensemble learning algorithms with only two experts 12 . The goal of these metrics is to measure the number of steps for the algorithm to reach a steady prediction for the concept.…”

Section: Introductionmentioning

confidence: 99%

“…Our main contributions are the introduction of quantative metrics of adaptiveness and consistency for N ‐expert ensemble learning algorithms. The metrics are computed from the mean hitting steps based on Markov chain models of the ensemble learning algorithms, which have not appeared in the literature other than the two‐expert case in our conference paper 12 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptiveness and consistency of a class of online ensemble learning algorithms

Young

Yao

Zhang

2020

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

Summary Expert based ensemble learning algorithms often serve as online learning algorithms for an unknown, possibly time‐varying, probability distribution. Their simplicity allows flexibility in design choices, leading to variations that balance adaptiveness and consistency. This article provides an analytical framework to quantify the adaptiveness and consistency of expert based ensemble learning algorithms. With properly selected states, the algorithms are modeled as a Markov chains. Then quantitative metrics of adaptiveness and consistency can be calculated through mathematical formulas, other than relying on numerical simulations. Results are derived for several popular ensemble learning algorithms. Success of the method has also been demonstrated in both simulation and experimental results.

show abstract