# Deep Sparse-coded Network (DSN)

 Title: Deep Sparse-coded Network (DSN) Author: Cha, Miriam; Gwon, Youngjune Lee ; Kung, H. T. Note: Order does not necessarily reflect citation order of authors. 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 Full Text & Related Files: dsn-gwon-cha-kung.pdf (714.4Kb; PDF) 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. Published Version: doi:10.1109/ICPR.2016.7900029 Terms of Use: This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAA Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:34903188 Downloads of this work: