GPdoemd: a python package for design of experiments for model discrimination

File Description SizeFormat 
1810.02561v1.pdfWorking paper119.57 kBAdobe PDFView/Open
Title: GPdoemd: a python package for design of experiments for model discrimination
Authors: Olofsson, S
Misener, R
Item Type: Working Paper
Abstract: GPdoemd is an open-source python package for design of experiments for model discrimination that uses Gaussian process surrogate models to approximate and maximise the divergence between marginal predictive distributions of rival mechanistic models. GPdoemd uses the divergence prediction to suggest a maximally informative next experiment.
Issue Date: 5-Oct-2018
URI: http://hdl.handle.net/10044/1/63850
Publisher: arXiv
Copyright Statement: © 2018 Simon Olofsson and Ruth Misener.
Sponsor/Funder: Commission of the European Communities
Engineering and Physical Sciences Research Council
Funder's Grant Number: 675251
EP/P016871/1
Keywords: cs.MS
stat.ML
Publication Status: Published
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx