Two distributed-state models for generating high-dimensional time series

MaRDI QIDQ5396632zbMATH OpenFDO

Authors Graham Taylor, Sam T. Roweis, Geoffrey Hinton

Publication date 3 February 2014

Full work available at URL http://www.jmlr.org/papers/v12/taylor11a.html

zbMATH Keywords

generative modelsmotion capturerestricted Boltzmann machinestime seriesunsupervised learning

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Universal approximation results for the temporal restricted Boltzmann machine and the recurrent temporal restricted Boltzmann machine
• Learning to represent spatial transformations with factored higher-order Boltzmann machines
• An infinite restricted Boltzmann machine
• Training restricted Boltzmann machines: an introduction
• scientific article; zbMATH DE number 2033137

Cited in

(5)

• Deep multimodal fusion: a hybrid approach
• Training energy-based models for time-series imputation
• scientific article; zbMATH DE number 2087338 (Why is no real title available?)
• An infinite restricted Boltzmann machine
• A unified theory of exact inference and learning in exponential family latent variable models

This page was built for publication: Two distributed-state models for generating high-dimensional time series

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5396632)