tag:joss.theoj.org,2005:/papers/tagged/binarized-neural-networksJournal of Open Source Software2020-01-16T00:24:45ZJournal of Open Source Softwarehttps://joss.theoj.orgtag:joss.theoj.org,2005:Paper/12172020-01-16T00:24:45Z2021-02-15T11:31:37ZLarq: An Open-Source Library for Training Binarized Neural Networksacceptedv0.7.12019-09-13 16:57:11 UTC452020-01-16 00:24:45 UTC520201746LukasGeigerPlumerai Research0000-0002-8697-9920PlumeraiTeamPlumerai Research10.21105/joss.01746https://doi.org/10.6084/m9.figshare.11619912.v1Pythonhttps://joss.theoj.org/papers/10.21105/joss.01746.pdfpython, tensorflow, keras, deep-learning, machine-learning, binarized-neural-networks, quantized-neural-networks, efficient-deep-learningtag:joss.theoj.org,2005:Paper/8102019-02-15T10:05:23Z2021-02-15T11:32:39ZBoltzMM: an R package for maximum pseudolikelihood estimation of fully-visible Boltzmann machinesaccepted0.1.32019-01-14 07:17:37 UTC342019-02-15 10:05:23 UTC420191193AndrewT.JonesSchool of Mathematics and Physics, University of Queensland, St. Lucia 4072, Queensland AustraliaJessicaJ.BagnallDepartment of Mathematics and Statistics, La Trobe University, Bundoora 3086, Victoria AustraliaHienD.NguyenDepartment of Mathematics and Statistics, La Trobe University, Bundoora 3086, Victoria Australia0000-0002-9958-432X10.21105/joss.01193https://doi.org/10.5281/zenodo.2563411R, C++https://joss.theoj.org/papers/10.21105/joss.01193.pdfartificial neural network, graphical model, maximum pseudolikelihood estimation, multivariate binary data, probability mass function