Learning deep autoregressive models for hierarchical data. Issue 7 (2021)

• Record Type: Journal Article
• Authors: Andersson, Carl R.; Wahlström, Niklas; Schön, Thomas B.
• Is Part Of: IFAC-PapersOnLine. Volume 54:Issue 7(2021)
• Page Start: 529
• Page End: 534
• Publication Date: 2021
• Subjects: Deep learning -- variational autoencoders -- nonlinear systems; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2021.08.414
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: We propose a model for hierarchical structured data as an extension to the stochastic temporal convolutional network. The proposed model combines an autoregressive model with a hierarchical variational autoencoder and downsampling to achieve superior computational complexity. We evaluate the proposed model on two different types of sequential data: speech and handwritten text. The results are promising with the proposed model achieving state-of-the-art performance.