Deep Learning: Concepts and Architectures

1. Front Matter

   Pages i-xii

   PDF

2. Deep Learning Architectures

   • Mohammad-Parsa Hosseini, Senbao Lu, Kavin Kamaraj, Alexander Slowikowski, Haygreev C. Venkatesh

   Pages 1-24

3. Theoretical Characterization of Deep Neural Networks

   • Piyush Kaul, Brejesh Lall

   Pages 25-63

4. Scaling Analysis of Specialized Tensor Processing Architectures for Deep Learning Models

   • Yuri Gordienko, Yuriy Kochura, Vlad Taran, Nikita Gordienko, Alexandr Rokovyi, Oleg Alienin et al.

   Pages 65-99

5. Assessment of Autoencoder Architectures for Data Representation

   • Karishma Pawar, Vahida Z. Attar

   Pages 101-132

6. The Encoder-Decoder Framework and Its Applications

   • Ahmad Asadi, Reza Safabakhsh

   Pages 133-167

7. Deep Learning for Learning Graph Representations

   • Wenwu Zhu, Xin Wang, Peng Cui

   Pages 169-210

8. Deep Neural Networks for Corrupted Labels

   • Ishan Jindal, Matthew Nokleby, Daniel Pressel, Xuewen Chen, Harpreet Singh

   Pages 211-235

9. Constructing a Convolutional Neural Network with a Suitable Capacity for a Semantic Segmentation Task

   • Yalong Jiang, Zheru Chi

   Pages 237-268

10. Using Convolutional Neural Networks to Forecast Sporting Event Results

    • Mu-Yen Chen, Ting-Hsuan Chen, Shu-Hong Lin

    Pages 269-285

11. Heterogeneous Computing System for Deep Learning

    • Mihaela Maliţa, George Vlǎduţ Popescu, Gheorghe M. Ştefan

    Pages 287-319

12. Progress in Neural Network Based Statistical Language Modeling

    • Anup Shrikant Kunte, Vahida Z. Attar

    Pages 321-339

13. Back Matter

    Pages 341-342

    PDF

This book introduces readers to the fundamental concepts of deep learning and offers practical insights into how this learning paradigm supports automatic mechanisms of structural knowledge representation. It discusses a number of multilayer architectures giving rise to tangible and functionally meaningful pieces of knowledge, and shows how the structural developments have become essential to the successful delivery of competitive practical solutions to real-world problems. The book also demonstrates how the architectural developments, which arise in the setting of deep learning, support detailed learning and refinements to the system design. Featuring detailed descriptions of the current trends in the design and analysis of deep learning topologies, the book offers practical guidelines and presents competitive solutions to various areas of language modeling, graph representation, and forecasting.

• Computational Intelligence
• Machine Learning
• Computer Vision
• Natural Language Processing
• Deep Learning Architectures
• Development Paradigms
• Pattern Recognition
• Image Processing
• Knowledge Representation
• AI

• Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada

  Witold Pedrycz

• Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

  Shyi-Ming Chen

Policies and ethics