Neural architecture search: a probabilistic approach

dc.contributor.author	Lut, Volodymyr
dc.date.accessioned	2020-06-17T23:31:24Z
dc.date.available	2020-06-17T23:31:24Z
dc.date.issued	2020
dc.identifier.citation	Lut, Volodymyr. Neural architecture search: a probabilistic approach : Master Thesis : manuscript rights / Volodymyr Lut ; Supervisor Yuriy Khoma, Vasilii Ganishev ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2020. – 27 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/2241
dc.language.iso	en	uk
dc.subject	neural architecture	uk
dc.subject	probabilistic approach	uk
dc.subject	encoding	uk
dc.title	Neural architecture search: a probabilistic approach	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	In this project, we introduce the Bayesian Optimization (BO) implementation of the NAS algorithm that is exploiting patterns found in most optimal unique architectures sampled from the most popular NAS dataset and benchmarking tool NASbench-101 (Dong and Yang, 2020a). The proposed solution leverages a novel approach to path-encoding and is designed to perform reproducible search even on a relatively small initial batch obtained from the random search. This implementation does not require any special hardware, it is publicly available.