Learning Centre

Gated Boltzmann machine in texture modeling

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.advisor Raiko, Tapani
dc.contributor.author Hao, Tele
dc.date.accessioned 2020-12-28T10:34:45Z
dc.date.available 2020-12-28T10:34:45Z
dc.date.issued 2012
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/100426
dc.description.abstract Recently, a new type of neural network method, namely deep learning, was discovered, which yielded excellent results in various tasks such as handwritten digit recognition, speech recognition and facial expression recognition. Different from traditional multi-layer perceptron learning methods (MLP), an unsupervised pre-training step before supervised learning is of huge importance in learning successful features. Also, it is argued that the deep architecture has more expressive power comparing to the conventional shallow networks, such as support vector machine or multi-layer perceptron's. Even though deep learning has yielded a large amount of world-class records in different tasks, there is little research on how the deep network can be used in texture analysis. For this particular problem, we consider the problem of modelling complex texture information using undirected probabilistic graphical models. Texture is a special type of data that one can better understand by considering its local structure. For that purpose, we propose a convolutional variant of the Gaussian gated Boltzmann machine (GGBM), inspired by the co-occurrence matrix in traditional texture analysis. We also link the proposed model to a much simpler Gaussian restricted Boltzmann machine where convolutional features are computed as a pre-processing step. The usefulness of the model is illustrated in texture classification and reconstruction experiments. en
dc.format.extent (11) + 70 s. + liitt. 3
dc.language.iso en en
dc.title Gated Boltzmann machine in texture modeling en
dc.contributor.school Perustieteiden korkeakoulu fi
dc.contributor.school School of Science en
dc.contributor.department Tietotekniikan laitos fi
dc.subject.keyword machine learning en
dc.subject.keyword unsupervised learning en
dc.subject.keyword deep learning en
dc.subject.keyword Boltzmann machine en
dc.subject.keyword texture analysis en
dc.subject.keyword pattern recognition en
dc.identifier.urn URN:NBN:fi:aalto-2020122859257
dc.programme.major Informaatiotekniikka fi
dc.programme.mcode T-61 fi
dc.type.ontasot Master's thesis en
dc.type.ontasot Pro gradu -tutkielma fi
dc.contributor.supervisor Karhunen, Juha
local.aalto.openaccess no
local.aalto.digifolder Aalto_03562
dc.rights.accesslevel closedAccess
local.aalto.idinssi 45744
dc.type.publication masterThesis
dc.type.okm G2 Pro gradu, diplomityö
local.aalto.digiauth ask

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