Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο: https://hdl.handle.net/20.500.14279/8203
Τίτλος: Echo-state conditional restricted boltzmann machines
Συγγραφείς: Chatzis, Sotirios P. 
metadata.dc.contributor.other: Χατζής, Σωτήριος Π.
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Λέξεις-κλειδιά: Restricted boltzmann machines;Εcho-state
Ημερομηνία Έκδοσης: 2014
Πηγή: 28th AAAI Conference on Artificial Intelligence, 2014, Québec, Canada, 27–31 July
Link: https://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/view/8134
Conference: AAAI Conference on Artificial Intelligence 
Περίληψη: Restricted Boltzmann machines (RBMs) are a powerful generative modeling technique, based on a complex graphical model of hidden (latent) variables. Conditional RBMs (CRBMs) are an extension of RBMs tailored to modeling temporal data. A drawback of CRBMs is their consideration of linear temporal dependencies, which limits their capability to capture complex temporal structure. They also require many variables to model long temporal dependencies, a fact that might provoke overfitting proneness. To resolve these issues, in this paper we propose the echo-state CRBM (ESCRBM): our model uses an echo-state network reservoir in the context of CRBMs to efficiently capture long and complex temporal dynamics, with much fewer trainable parameters compared to conventional CRBMs. In addition, we introduce an (implicit) mixture of ES-CRBM experts (im-ESCRBM) to enhance even further the capabilities of our ES-RBM model. The introduced im-ES-CRBM allows for better modeling temporal observations which might comprise a number of latent or observable subpatterns that alternate in a dynamic fashion. It also allows for performing sequence segmentation using our framework. We apply our methods to sequential data modeling and classification experiments using public datasets.
URI: https://hdl.handle.net/20.500.14279/8203
Type: Conference Papers
Affiliation: Cyprus University of Technology 
Εμφανίζεται στις συλλογές:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation

CORE Recommender
Δείξε την πλήρη περιγραφή του τεκμηρίου

Page view(s) 20

448
Last Week
0
Last month
8
checked on 28 Αυγ 2024

Google ScholarTM

Check


Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα