A probability density function generator based on neural networks

Chen, CH; Song, F; Hwang, FJ; Wu, L

A probability density function generator based on neural networks

Chen, CH Song, F Hwang, FJ

Wu, L

Permalink

Publication Type:: Journal Article
Citation:: Physica A: Statistical Mechanics and its Applications, 2020, 541
Issue Date:: 2020-03-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 30 Nov 2021

Adobe PDF

Download full textAdobe PDF (712.02 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Chen, CH	en_US
dc.contributor.author	Song, F	en_US
dc.contributor.author	Hwang, FJ https://orcid.org/0000-0002-1741-5590	en_US
dc.contributor.author	Wu, L	en_US
dc.date.issued	2020-03-01	en_US
dc.identifier.citation	Physica A: Statistical Mechanics and its Applications, 2020, 541	en_US
dc.identifier.issn	0378-4371	en_US
dc.identifier.uri	http://hdl.handle.net/10453/136782
dc.description.abstract	© 2019 Elsevier B.V. In order to generate a probability density function (PDF) for fitting the probability distributions of practical data, this study proposes a deep learning method which consists of two stages: (1) a training stage for estimating the cumulative distribution function (CDF) and (2) a performing stage for predicting the corresponding PDF. The CDFs of common probability distributions can be utilised as activation functions in the hidden layers of the proposed deep learning model for learning actual cumulative probabilities, and the differential equation of the trained deep learning model can be used to estimate the PDF. Numerical experiments with single and mixed distributions are conducted to evaluate the performance of the proposed method. The experimental results show that the values of both CDF and PDF can be precisely estimated by the proposed method.	en_US
dc.relation.ispartof	Physica A: Statistical Mechanics and its Applications	en_US
dc.relation.isbasedon	10.1016/j.physa.2019.123344	en_US
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject.classification	Fluids & Plasmas	en_US
dc.title	A probability density function generator based on neural networks	en_US
dc.type	Journal Article
utslib.citation.volume	541	en_US
utslib.for	0105 Mathematical Physics	en_US
utslib.for	0206 Quantum Physics	en_US
utslib.for	0102 Applied Mathematics	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2021-11-30T00:00:00+1100
pubs.publication-status	Accepted	en_US
pubs.volume	541	en_US

Abstract:

© 2019 Elsevier B.V. In order to generate a probability density function (PDF) for fitting the probability distributions of practical data, this study proposes a deep learning method which consists of two stages: (1) a training stage for estimating the cumulative distribution function (CDF) and (2) a performing stage for predicting the corresponding PDF. The CDFs of common probability distributions can be utilised as activation functions in the hidden layers of the proposed deep learning model for learning actual cumulative probabilities, and the differential equation of the trained deep learning model can be used to estimate the PDF. Numerical experiments with single and mixed distributions are conducted to evaluate the performance of the proposed method. The experimental results show that the values of both CDF and PDF can be precisely estimated by the proposed method.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/136782