Modeling spatiotemporal information with convolutional gated networks

Examensarbete för masterexamen

Please use this identifier to cite or link to this item:
Download file(s):
File Description SizeFormat 
248944.pdfFulltext1.28 MBAdobe PDFView/Open
Type: Examensarbete för masterexamen
Master Thesis
Title: Modeling spatiotemporal information with convolutional gated networks
Authors: Roos, Filip de
Abstract: In this thesis, a recently proposed bilinear model for predicting spatiotemporal data has been implemented and extended. The model was trained in an unsupervised manner and uses spatiotemporal synchrony to encode transformations between inputs of a sequence up to a time t, in order to predict the next input at t + 1. A convolutional version of the model was developed in order to reduce the number of parameters and improve the predictive capabilities. The original and the convolutional models were tested and compared on a dataset containing videos of bouncing balls and both versions are able to predict the motion of the balls. The developed convolutional version halved the 4-step prediction loss while reducing the number of parameters by a factor of 159 compared to the original model. Some important differences between the models are discussed in the thesis and suggestions for further improvements of the convolutional model are identified and presented.
Keywords: Signalbehandling;Informations- och kommunikationsteknik;Signal Processing;Information & Communication Technology
Issue Date: 2016
Publisher: Chalmers tekniska högskola / Institutionen för tillämpad mekanik
Chalmers University of Technology / Department of Applied Mechanics
Series/Report no.: Diploma work - Department of Applied Mechanics, Chalmers University of Technology, Göteborg, Sweden : 2016:83
Collection:Examensarbeten för masterexamen // Master Theses

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