Learning deep dynamical models from image pixels

File Description SizeFormat 
1410.7550v1.pdfWorking paper1.32 MBAdobe PDFView/Open
Title: Learning deep dynamical models from image pixels
Authors: Wahlström, N
Schön, TB
Deisenroth, MP
Item Type: Report
Abstract: Modeling dynamical systems is important in many disciplines, e.g., control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional observations. In these cases, system identification, i.e., finding the measurement mapping and the transition mapping (system dynamics) in latent space can be challenging. For linear system dynamics and measurement mappings efficient solutions for system identification are available. However, in practical applications, the linearity assumptions does not hold, requiring non-linear system identification techniques. If additionally the observations are high-dimensional (e.g., images), non-linear system identification is inherently hard. To address the problem of non-linear system identification from high-dimensional observations, we combine recent advances in deep learning and system identification. In particular, we jointly learn a low-dimensional embedding of the observation by means of deep auto-encoders and a predictive transition model in this low-dimensional space. We demonstrate that our model enables learning good predictive models of dynamical systems from pixel information only.
Issue Date: 31-Dec-2014
URI: http://hdl.handle.net/10044/1/18321
Copyright Statement: © 2014 The Authors
Notes: 10 pages, 11 figures
Appears in Collections:Computing

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx