Deep Sparse-coded Network (DSN) Article Swipe

View

Related Concepts

Autoencoder Neural coding Computer science Pooling Artificial intelligence Deep learning Pattern recognition (psychology) Coding (social sciences) Algorithm Sparse matrix Encoder Convolutional neural network Hessian matrix Theoretical computer science Mathematics Physics Quantum mechanics Operating system Statistics Gaussian Applied mathematics

Youngjune Gwon , Miriam Cha , H. T. Kung ·

YOU? · · 2016 · Open Access · · DOI: https://doi.org/10.1109/icpr.2016.7900029 · OA: W2607813869

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.