HYPERPARAMETER OPTIMIZATION BASED ON A PRIORI AND A POSTERIORI KNOWLEDGE ABOUT CLASSIFICATION PROBLEM
Journal: Scientific and Technical Journal of Information Technologies, Mechanics and Optics (Vol.20, No. 6)Publication Date: 2020-12-03
Authors : Smirnova V.S. Shalamov V.V. Efimova V.A. Filchenkov A.A.;
Page : 828-834
Keywords : machine learning; classification; hyperparameter optimization; Bayesian optimization; Gaussian processes;
Abstract
Subject of Research. The paper deals with Bayesian method for hyperparameter optimization of algorithms, used in machine learning for classification problems. A comprehensive survey is carried out about using a priori and a posteriori knowledge in classification task for hyperparameter optimization quality improvement. Method. The existing Bayesian optimization algorithm for hyperparameter setting in classification problems was expanded. We proposed a target function modification calculated on the basis of hyperparameters optimized for the similar problems and a metric for determination of similarity classification problems based on generated meta-features. Main Results. Experiments carried out on the real-world datasets from OpenML database have confirmed that the proposed algorithm achieves usually significantly better performance results than the existing Bayesian optimization algorithm within a fixed time limit. Practical Relevance. The proposed algorithm can be used for hyperparameter optimization in any classification problem, for example, in medicine, image processing or chemistry.
Other Latest Articles
- CONCEPT OF DIGITAL TWINS AT LIFE CYCLE STAGES OF PRODUCTION SYSTEMS
- METHOD OF JOINT CLUSTERING IN NETWORK AND CORRELATION SPACES
- FAST MOTION ESTIMATION ALGORITHM FOR HEVC VIDEO CODEC
- EFFECT OF PLANT EXTRACTS ON ACTIVITY OF STAPHYLOCOCCUS AUREUS BY ELECTROCHEMICAL BIOTESTING
- APPLICATION FEATURES OF OPTICAL POLYMERS IN OPTICAL SYSTEMS DESIGN
Last modified: 2020-12-05 01:13:19