Clues to quality of journals
Open Access Policy of Helmholtz Association 2016
CC Licencences
Publication Metrics
Home
Deutsch
New EVA Application
Advanced Search
Browse by ...
Publication overview
Statistics (last 5 years)
OA Publications
Submit Publication
Import publication from...
Report missing publication
Contact persons
Help
Text
Endnote (RIS)
BibTeX |
|
as soon as is submitted to ZB.
Bayesian optimization and attribute adjustment.
In: (34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018, 6-10 August 2018, Monterey, United States). 2018. 1042-1052 ( ; 2)
Automatic design via Bayesian optimization holds great promise given the constant increase of available data across domains. However, it faces difficulties from high-dimensional, potentially discrete, search spaces. We propose to probabilistically embed inputs into a lower dimensional, continuous latent space, where we perform gradient-based optimization guided by a Gaussian process. Building on variational autoncoders, we use both labeled and unlabeled data to guide the encoding and increase its accuracy. In addition, we propose an adversarial extension to render the latent representation invariant with respect to specific design attributes, which allows us to transfer these attributes across structures. We apply the framework both to a functional-protein dataset and to perform optimization of drag coefficients directly over high-dimensional shapes without incorporating domain knowledge or handcrafted features.
Annotations
Special Publikation
Hide on homepage
Publication type
Article: Conference contribution
Language
english
Publication Year
2018
HGF-reported in Year
2018
ISSN (print) / ISBN
9781510871601
Conference Title
34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018
Conference Date
6-10 August 2018
Conference Location
Monterey, United States
Quellenangaben
Volume: 2,
Pages: 1042-1052
Institute(s)
Institute of Radiation Medicine (IRM)
POF-Topic(s)
30203 - Molecular Targets and Therapies
Research field(s)
Radiation Sciences
PSP Element(s)
G-501300-001
Scopus ID
85059376675
Erfassungsdatum
2019-01-11