Person:

Cha, Miriam

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.

As an unsupervised learning method, sparse coding can discover high-level representations for an input in a large variety of learning problems. Under semi-supervised settings, sparse coding is used to extract features for a supervised task such as classification. While sparse representations learned from unlabeled data independently of the supervised task perform well, we argue that sparse coding should also be built as a holistic learning unit optimizing on the supervised task objectives more explicitly. In this paper, we propose sparse-coded net, a feedforward model that integrates sparse coding and task-driven output layers, and describe training methods in detail. After pretraining a sparse-coded net via semi-supervised learning, we optimize its task-specific performance in a novel backpropagation algorithm that can traverse nonlinear feature pooling operators to update the dictionary. Thus, sparse-coded net can be applied to supervised dictionary learning. We evaluate sparse-coded net with classification problems in sound, image, and text data. The results confirm a significant improvement over semi-supervised learning as well as superior classification performance against deep stacked autoencoder neural network and GMM-SVM pipelines in small to medium-scale settings.