Boltzmann Machines for signals decomposition. Application to Parkinson's Disease control

Abstract : This article presents a new method of decomposition of signals with an unsupervised training model: the continuous Restricted Boltzmann Machine (cRBM) based on the structure of the Diffusion Network. An application for the detection of High-Voltage Spindle (HVS) in signals recorded in the brain is also presented.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02197049
Contributor : Frédéric Davesne <>
Submitted on : Monday, July 29, 2019 - 10:48:53 PM
Last modification on : Thursday, August 1, 2019 - 2:13:52 AM

File

souriau355.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02197049, version 1

Citation

Rémi Souriau, Vincent Vigneron, Jean Lerbet, Hsin Chen. Boltzmann Machines for signals decomposition. Application to Parkinson's Disease control. XXVIIème Colloque francophone de traitement du signal et des images (GRETSI 2019), Aug 2019, Lille, France. ⟨hal-02197049⟩

Share

Metrics

Record views

22

Files downloads

11