Deep Learning through Sparse and Low-Rank Modeling

Helps users improve the performance and interpretability of Deep Learning models by explaining how to integrate sparse and low-rank methods

Zhangyang Wang (Author), Yun Fu (Author), Thomas S. Huang (Author)

9780128136591, Elsevier Science

Paperback, published 12 April 2019

296 pages
23.4 x 19 x 1.9 cm, 0.57 kg

Deep Learning through Sparse Representation and Low-Rank Modeling bridges classical sparse and low rank models—those that emphasize problem-specific Interpretability—with recent deep network models that have enabled a larger learning capacity and better utilization of Big Data. It shows how the toolkit of deep learning is closely tied with the sparse/low rank methods and algorithms, providing a rich variety of theoretical and analytic tools to guide the design and interpretation of deep learning models. The development of the theory and models is supported by a wide variety of applications in computer vision, machine learning, signal processing, and data mining.

1. Introduction2. Bi-Level Sparse Coding: A Hyperspectral Image Classification Example3. Deep l0 Encoders: AModel Unfolding Example4. Single Image Super-Resolution: FromSparse Coding to Deep Learning5. From Bi-Level Sparse Clustering to Deep Clustering6. Signal Processing7. Dimensionality Reduction8. Action Recognition9. Style Recognition and Kinship Understanding10. Image Dehazing: Improved Techniques11. Biomedical Image Analytics: Automated Lung Cancer Diagnosis

Subject Areas: Computer vision [UYQV]