Derivations of the Enhanced Gradient for the Boltzmann Machine

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en Ilin, Alexander Cho, KyungHyun Raiko, Tapani 2017-04-25T09:00:39Z 2017-04-25T09:00:39Z 2011
dc.identifier.isbn 978-952-60-4295-4
dc.identifier.issn 1799-490X
dc.description.abstract This technical report is extends the conference paper [1] and the abstract [2] with detailed derivations and proofs. First we recap notation that we use on the Boltzmann machine and its learning. Then we define transformations for the machine where some of its bits are flipped for all samples, and show the equivalence of the transformed model to the original one. Then we show that traditional update rules are not invariant to the transformations, propose a new update rule called theenhanced gradient, and finally show its invariance to the transformations. en
dc.format.extent 9
dc.language.iso en en
dc.publisher Aalto University en
dc.publisher Aalto-yliopisto fi
dc.relation.ispartofseries Aalto University publication series SCIENCE+TECHNOLOGY en
dc.relation.ispartofseries 20/2011
dc.subject.other Computer science en
dc.title Derivations of the Enhanced Gradient for the Boltzmann Machine en
dc.type D4 Julkaistu kehittämis- tai tutkimusraportti tai -selvitys fi Perustieteiden korkeakoulu fi School of Science en
dc.contributor.department Tietotekniikan laitos fi
dc.contributor.department Department of Computer Science en
dc.subject.keyword enhanced gradient en
dc.subject.keyword boltzmann machine en
dc.subject.keyword sample index en
dc.identifier.urn URN:NBN:fi:aalto-201704243665
dc.type.dcmitype text en

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication