Using Convolutional Autoencoders to Improve Classification Performance

Keywords
Loading...
Thumbnail Image
Issue Date
2015-07-13
Language
en
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This thesis combines convolutional neural networks with autoencoders, to form a convolutional autoencoder. Several techniques related to the realisation of a convolutional autoencoder are investigated, and an attempt is made to use these models to improve performance on an audio-based phone classification task.
Description
Citation
Faculty
Faculteit der Sociale Wetenschappen