Gwon, YoungjuneCha, MiriamCampbell, WilliamKung, H.Dagli, Charlie K.2023-01-232016-09Gwon, Youngjune, Miriam Cha, William Campbell, H. T. Kung, and Charlie K. Dagli. "Sparse-coded net model and applications." In Machine Learning for Signal Processing (MLSP), 2016 IEEE 26th International Workshop on, pp. 1-6. IEEE, 2016.https://nrs.harvard.edu/URN-3:HUL.INSTREPOS:37374078As 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.en-USConference Paper2023-01-2310.1109/mlsp.2016.7738828