Boltzmann Machine and its Applications in Image Recognition

Abstract : The overfitting problems commonly exist in neural networks and RBM models. In order to alleviate the overfitting problem, lots of research has been done. This paper built Weight uncertainty RBM model based on maximum likelihood estimation. And in the experimental section, this paper verified the effectiveness of the Weight uncertainty Deep Belief Network and the Weight uncertainty Deep Boltzmann Machine. In order to improve the images recognition ability, we introduce the spike-and-slab RBM (ssRBM) to our Weight uncertainty RBM and then build the Weight uncertainty spike-and-slab Deep Boltzmann Machine (wssDBM). The experiments showed that, the Weight uncertainty RBM, Weight uncertainty DBN and Weight uncertainty DBM were effective compared with the dropout method. At last, we validate the effectiveness of wssDBM in experimental section.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/hal-01614991
Contributor : Hal Ifip <>
Submitted on : Wednesday, October 11, 2017 - 4:57:51 PM
Last modification on : Friday, November 3, 2017 - 10:24:06 PM
Long-term archiving on : Friday, January 12, 2018 - 3:38:50 PM

File

433802_1_En_12_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Shifei Ding, Jian Zhang, Nan Zhang, Yanlu Hou. Boltzmann Machine and its Applications in Image Recognition. 9th International Conference on Intelligent Information Processing (IIP), Nov 2016, Melbourne, VIC, Australia. pp.108-118, ⟨10.1007/978-3-319-48390-0_12⟩. ⟨hal-01614991⟩

Share

Metrics

Record views

83

Files downloads

110