Aarhus Universitets segl

English

Du er her: AU » Om AU » Organisation » Variational Neural Networks implementation in Pytorch and...

Om AU

Variational Neural Networks implementation in Pytorch and JAX[Formula presented]

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

Standard

Variational Neural Networks implementation in Pytorch and JAX[Formula presented]. / Oleksiienko, Illia; Tran, Dat Thanh; Iosifidis, Alexandros.

I: Software Impacts, Bind 14, 100431, 11.2022.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

Harvard

Oleksiienko, I, Tran, DT & Iosifidis, A 2022, 'Variational Neural Networks implementation in Pytorch and JAX[Formula presented]', Software Impacts, bind 14, 100431. https://doi.org/10.1016/j.simpa.2022.100431

APA

Oleksiienko, I., Tran, D. T., & Iosifidis, A. (2022). Variational Neural Networks implementation in Pytorch and JAX[Formula presented]. Software Impacts, 14, [100431]. https://doi.org/10.1016/j.simpa.2022.100431

CBE

Oleksiienko I, Tran DT, Iosifidis A. 2022. Variational Neural Networks implementation in Pytorch and JAX[Formula presented]. Software Impacts. 14:Article 100431. https://doi.org/10.1016/j.simpa.2022.100431

MLA

Oleksiienko, Illia, Dat Thanh Tran, og Alexandros Iosifidis. "Variational Neural Networks implementation in Pytorch and JAX[Formula presented]". Software Impacts. 2022. 14. https://doi.org/10.1016/j.simpa.2022.100431

Vancouver

Oleksiienko I, Tran DT, Iosifidis A. Variational Neural Networks implementation in Pytorch and JAX[Formula presented]. Software Impacts. 2022 nov.;14:100431. doi: 10.1016/j.simpa.2022.100431

Author

Oleksiienko, Illia ; Tran, Dat Thanh ; Iosifidis, Alexandros. / Variational Neural Networks implementation in Pytorch and JAX[Formula presented]. I: Software Impacts. 2022 ; Bind 14.

Bibtex

@article{5b8d9a087955445d8e7762846d2fb464,
title = "Variational Neural Networks implementation in Pytorch and JAX[Formula presented]",
abstract = "Bayesian Neural Networks consider a distribution over the network's weights, which provides a tool to estimate the uncertainty of a neural network by sampling different models for each input. Variational Neural Networks (VNNs) consider a probability distribution over each layer's outputs and generate parameters for it with the corresponding sub-layers. We provide two Python implementations of VNNs with PyTorch and JAX machine learning libraries that ensure reproducibility of the experimental results and allow implementing uncertainty estimation methods easily in other projects.",
keywords = "Bayesian deep learning, Bayesian Neural Networks, JAX, PyTorch, Uncertainty estimation",
author = "Illia Oleksiienko and Tran, {Dat Thanh} and Alexandros Iosifidis",
note = "Publisher Copyright: {\textcopyright} 2022 The Author(s)",
year = "2022",
month = nov,
doi = "10.1016/j.simpa.2022.100431",
language = "English",
volume = "14",
journal = "Software Impacts",
issn = "2665-9638",
publisher = "Elsevier BV",

}

RIS

TY - JOUR

T1 - Variational Neural Networks implementation in Pytorch and JAX[Formula presented]

AU - Oleksiienko, Illia

AU - Tran, Dat Thanh

AU - Iosifidis, Alexandros

N1 - Publisher Copyright: © 2022 The Author(s)

PY - 2022/11

Y1 - 2022/11

N2 - Bayesian Neural Networks consider a distribution over the network's weights, which provides a tool to estimate the uncertainty of a neural network by sampling different models for each input. Variational Neural Networks (VNNs) consider a probability distribution over each layer's outputs and generate parameters for it with the corresponding sub-layers. We provide two Python implementations of VNNs with PyTorch and JAX machine learning libraries that ensure reproducibility of the experimental results and allow implementing uncertainty estimation methods easily in other projects.

AB - Bayesian Neural Networks consider a distribution over the network's weights, which provides a tool to estimate the uncertainty of a neural network by sampling different models for each input. Variational Neural Networks (VNNs) consider a probability distribution over each layer's outputs and generate parameters for it with the corresponding sub-layers. We provide two Python implementations of VNNs with PyTorch and JAX machine learning libraries that ensure reproducibility of the experimental results and allow implementing uncertainty estimation methods easily in other projects.

KW - Bayesian deep learning

KW - Bayesian Neural Networks

KW - JAX

KW - PyTorch

KW - Uncertainty estimation

UR - http://www.scopus.com/inward/record.url?scp=85140775113&partnerID=8YFLogxK

U2 - 10.1016/j.simpa.2022.100431

DO - 10.1016/j.simpa.2022.100431

M3 - Journal article

AN - SCOPUS:85140775113

VL - 14

JO - Software Impacts

JF - Software Impacts

SN - 2665-9638

M1 - 100431

ER -