Publication: Deep Sparse-coded Network (DSN)
Open/View Files
Date
2015
Published Version
Journal Title
Journal ISSN
Volume Title
Publisher
The Harvard community has made this article openly available. Please share how this access benefits you.
Citation
Gwon, Youngjune, Miriam Cha; H. T. Kung. 2016. Deep Sparse-coded Network (DSN). In Proceedings of 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, December 4-8, 2016. doi: 10.1109/ICPR.2016.7900029
Research Data
Abstract
We introduce Deep Sparse-coded Network (DSN), a deep architecture based on sparse coding and dictionary learning. Key advantage of our approach is two-fold. By interlacing max pooling with sparse coding layer, we achieve nonlinear activation analogous to neural networks, but suffering less from diminished gradients. We use a novel backpropagation algorithm to finetune our DSN beyond the pretraining by layer-by-layer sparse coding and dictionary learning. We build an experimental 4-layer DSN with the `1-regularized LARS and greedy-`0 OMP and demonstrate superior performance over deep stacked autoencoder on CIFAR-10.
Description
Other Available Sources
Keywords
Terms of Use
This article is made available under the terms and conditions applicable to Other Posted Material (LAA), as set forth at Terms of Service