Taking the Human Out of the Loop: A Review of Bayesian Optimization

Shahriari, Bobak; Swersky, Kevin; Wang, Ziyu; Adams, Ryan P.; Freitas, Nando de

doi:10.1109/jproc.2015.2494218

Cited by 4,024 publications

(2,989 citation statements)

References 87 publications

Supporting

Mentioning

2,755

Contrasting

Unclassified

Order By: Relevance

“…The optimization algorithm used hereafter to minimize f (x) over the domain belongs to a class of Bayesian optimization algorithms (Mockus, 1989;Shahriari et al, 2016). The Bayesian aspect refers to placing a random process prior Y on the unknown 5 function f (possibly computationally expensive) and updating its probability distribution thanks to available evaluation results, and the optimization part relies on using conditional distributions of Y to iteratively choose points with the identification of f 's global optimum/optimizer(s) in view.…”

Section: Optimization Methodologymentioning

confidence: 99%

Contaminant source localization via Bayesian global optimization

Pirot¹,

Krityakierne²,

Ginsbourger³

et al. 2017

Preprint

View full text Add to dashboard Cite

Abstract. A Bayesian optimization approach to localize a contaminant source is proposed. The localization problem is illustrated with two 2D synthetic cases which display sharp transmissivity contrasts and specific connectivity patterns. These cases generate highly non-linear objective functions that present multiple local minima. A derivative-free global optimization algorithm relying on a Gaussian Process model and on the Expected Improvement criterion is used to efficiently localize the minimum of the objective function which identifies the contaminant source. In addition, the generated objective functions 5 are made available as a benchmark to further allow the comparison of optimization algorithms on functions characterized by multiple minima and inspired by concrete field applications.

show abstract

Section: Optimization Methodologymentioning

confidence: 99%

Contaminant source localization via Bayesian global optimization

Pirot¹,

Krityakierne²,

Ginsbourger³

et al. 2017

Preprint

View full text Add to dashboard Cite

show abstract

“…Solution Based on Bayesian Optimization. Bayesian optimization is a statistical framework that uses information gained from past experiments to model and minimize an arbitrary objective function, and it works by building and querying cheap surrogate models which estimate the behavior of real objective functions which are expensive to evaluate [29]. Surrogate models are typically built using Gaussian process regression (GPR).…”

Section: Electromechanical Codesign Formulationmentioning

confidence: 99%

“…According to the research in [29][30][31], the new point x N+1 is obtained by a search algorithm, and the new …”

Section: Electromechanical Codesign Formulationmentioning

confidence: 99%

Design, Fabrication, and Testing of Active Skin Antenna with 3D Printing Array Framework

Zhou

Kang

et al. 2017

International Journal of Antennas and Propagation

View full text Add to dashboard Cite

An active skin antenna with structural load-bearing and electromagnetic functions is usually installed in the structural surface of mobile vehicles such as aircrafts, warships, and high-speed train. This paper presents the design, fabrication, and testing of a novel active skin antenna which consists of an encapsulation shell, antenna skin, and RF and beam control circuits. The antenna skin which consists of the facesheet, honeycomb, array framework, and microstrip antenna elements was designed by using Bayesian optimization, in order to improve the design efficiency. An active skin antenna prototype with 32 microstrip antenna elements was fabricated by using a hybrid manufacturing method. In this method, 3D printing technology was applied to fabricate the array framework, and the different layers were bonded to form the final antenna skin by using traditional composite process. Some experimental testing was conducted, and the testing results validate the feasibility the proposed antenna skin structure. The proposed design and fabrication technique is suitable for the development of conformal load-bearing antenna or smart skin antenna installed in the structural surface of aircraft, warships, and armored vehicles.

show abstract

“…automatic Machine Learning (aML) in bringing the human-out-of-the-loop is the grand goal of ML and works well in many cases with "big data" [16].…”

Section: Glossary and Key Termsmentioning

confidence: 99%

Machine Learning for Health Informatics

Holzinger¹

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Machine Learning (ML) studies algorithms which can learn from data to gain knowledge from experience and to make decisions and predictions. Health Informatics (HI) studies the effective use of probabilistic information for decision making. The combination of both has greatest potential to rise quality, efficacy and efficiency of treatment and care. Health systems worldwide are confronted with "big data" in high dimensions, where the inclusion of a human is impossible and automatic ML (aML) show impressive results. However, sometimes we are confronted with complex data, "little data", or rare events, where aMLapproaches suffer of insufficient training samples. Here interactive ML (iML) may be of help, particularly with a doctor-in-the-loop, e.g. in subspace clustering, k-Anonymization, protein folding and protein design. However, successful application of ML for HI needs an integrated approach, fostering a concerted effort of four areas: (1) data science, (2) algorithms (with focus on networks and topology (structure), and entropy (time), (3) data visualization, and last but not least (4) privacy, data protection, safety & security.

show abstract

Taking the Human Out of the Loop: A Review of Bayesian Optimization

Cited by 4,024 publications

References 87 publications

Contaminant source localization via Bayesian global optimization

Contaminant source localization via Bayesian global optimization

Design, Fabrication, and Testing of Active Skin Antenna with 3D Printing Array Framework

Machine Learning for Health Informatics

Contact Info

Product

Resources

About