Deep Learning through Sparse and Low-Rank Modeling

Deep Learning through Sparse and Low-Rank Modeling

by Zhangyang Wang, Yun Fu, Thomas S. Huang
Released April 2019
Publisher(s): Academic Press
ISBN: 9780128136607

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

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.

This book will be highly useful for researchers, graduate students and practitioners working in the fields of computer vision, machine learning, signal processing, optimization and statistics.

  • Combines classical sparse and low-rank models and algorithms with the latest advances in deep learning networks
  • Shows how the structure and algorithms of sparse and low-rank methods improves the performance and interpretability of Deep Learning models
  • Provides tactics on how to build and apply customized deep learning models for various applications

Table of contents

  1. Cover image
  2. Title page
  3. Table of Contents
  4. Copyright
  5. Contributors
  6. About the Editors
  7. Preface
  8. Acknowledgments
  9. Chapter 1: Introduction
    1. Abstract
    2. 1.1. Basics of Deep Learning
    3. 1.2. Basics of Sparsity and Low-Rankness
    4. 1.3. Connecting Deep Learning to Sparsity and Low-Rankness
    5. 1.4. Organization
    6. References
  10. Chapter 2: Bi-Level Sparse Coding: A Hyperspectral Image Classification Example
    1. Abstract
    2. 2.1. Introduction
    3. 2.2. Formulation and Algorithm
    4. 2.3. Experiments
    5. 2.4. Conclusion
    6. 2.5. Appendix
    7. References
  11. Chapter 3: Deep ℓ0 Encoders: A Model Unfolding Example
    1. Abstract
    2. 3.1. Introduction
    3. 3.2. Related Work
    4. 3.3. Deep ℓ0 Encoders
    5. 3.4. Task-Driven Optimization
    6. 3.5. Experiment
    7. 3.6. Conclusions and Discussions on Theoretical Properties
    8. References
  12. Chapter 4: Single Image Super-Resolution: From Sparse Coding to Deep Learning
    1. Abstract
    2. 4.1. Robust Single Image Super-Resolution via Deep Networks with Sparse Prior
    3. 4.2. Learning a Mixture of Deep Networks for Single Image Super-Resolution
    4. References
  13. Chapter 5: From Bi-Level Sparse Clustering to Deep Clustering
    1. Abstract
    2. 5.1. A Joint Optimization Framework of Sparse Coding and Discriminative Clustering
    3. 5.2. Learning a Task-Specific Deep Architecture for Clustering
    4. References
  14. Chapter 6: Signal Processing
    1. Abstract
    2. 6.1. Deeply Optimized Compressive Sensing
    3. 6.2. Deep Learning for Speech Denoising
    4. References
  15. Chapter 7: Dimensionality Reduction
    1. Abstract
    2. 7.1. Marginalized Denoising Dictionary Learning with Locality Constraint
    3. 7.2. Learning a Deep ℓ∞ Encoder for Hashing
    4. References
  16. Chapter 8: Action Recognition
    1. Abstract
    2. 8.1. Deeply Learned View-Invariant Features for Cross-View Action Recognition
    3. 8.2. Hybrid Neural Network for Action Recognition from Depth Cameras
    4. 8.3. Summary
    5. References
  17. Chapter 9: Style Recognition and Kinship Understanding
    1. Abstract
    2. 9.1. Style Classification by Deep Learning
    3. 9.2. Visual Kinship Understanding
    4. 9.3. Research Challenges and Future Works
    5. References
  18. Chapter 10: Image Dehazing: Improved Techniques
    1. Abstract
    2. 10.1. Introduction
    3. 10.2. Review and Task Description
    4. 10.3. Task 1: Dehazing as Restoration
    5. 10.4. Task 2: Dehazing for Detection
    6. 10.5. Conclusion
    7. References
  19. Chapter 11: Biomedical Image Analytics: Automated Lung Cancer Diagnosis
    1. Abstract
    2. Acknowledgements
    3. 11.1. Introduction
    4. 11.2. Related Work
    5. 11.3. Methodology
    6. 11.4. Experiments
    7. 11.5. Conclusion
    8. References
  20. Index

Product information

  • Title: Deep Learning through Sparse and Low-Rank Modeling
  • Author(s): Zhangyang Wang, Yun Fu, Thomas S. Huang
  • Release date: April 2019
  • Publisher(s): Academic Press
  • ISBN: 9780128136607