 Название: Learning in Energy-Efficient Neuromorphic Computing: Algorithm and Architecture Co-Design
Автор: Nan Zheng, Pinaki Mazumder
Издательство: Wiley-IEEE Press
Год: 2020
Страниц: 289
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB
Explains current co-design and co-optimization methodologies for building hardware neural networks and algorithms for machine learning applications.
Machine learning, especially deep learning, has emerged as an important discipline through which many conventionally difficult problems, such as pattern recognition, decision making, and natural language processing, can be addressed. Nowadays, millions and even billions of neural networks are running in data centers, personal computers and portable devices to perform various tasks. In the future, it is expected that more complex neural networks with larger sizes will be needed. Such a trend demands specialized hardware to accommodate the ever-increasing requirements on power consumption and response time.
In this book, we focus on the topic of how to build energy-efficient hardware for neural networks with a learning capability. This book strives to provide co-design and co-optimization methodologies for building hardware neural networks that can learn to perform various tasks. The book provides a complete picture from high-level algorithms to low-level implementation details. Hardware-friendly algorithms are developed with the objective to ease implementation in hardware, whereas special hardware architectures are proposed to exploit the unique features of the algorithms.
- Includes cross-layer survey of hardware accelerators for neuromorphic algorithms
- Covers the co-design of architecture and algorithms with emerging devices for much-improved computing efficiency
- Focuses on the co-design of algorithms and hardware, which is especially critical for using emerging devices, such as traditional memristors or diffusive memristors, for neuromorphic computing
Learning in Energy-Efficient Neuromorphic Computing: Algorithm and Architecture Co-Design is an ideal resource for researchers, scientists, software engineers, and hardware engineers dealing with the ever-increasing requirement on power consumption and response time. It is also excellent for teaching and training undergraduate and graduate students about the latest generation neural networks with powerful learning capabilities.
Contents:
Preface xi
Acknowledgment xix
1 Overview 1
1.1 History of Neural Networks 1
1.2 Neural Networks in Software 2
1.2.1 Artificial Neural Network 2
1.2.2 Spiking Neural Network 3
1.3 Need for Neuromorphic Hardware 3
1.4 Objectives and Outlines of the Book 5
2 Fundamentals and Learning of Artificial Neural Networks 11
2.1 Operational Principles of Artificial Neural Networks 11
2.1.1 Inference 11
2.1.2 Learning 13
2.2 Neural Network Based Machine Learning 16
2.2.1 Supervised Learning 17
2.2.2 Reinforcement Learning 20
2.2.3 Unsupervised Learning 22
2.2.4 Case Study: Action-Dependent Heuristic Dynamic Programming 23
...
2.5 Deep Learning 41
...
3 Artificial Neural Networks in Hardware 61
3.1 Overview 61
3.2 General-Purpose Processors 62
3.3 Digital Accelerators 63
3.3.1 A Digital ASIC Approach 63
3.4 Analog/Mixed-Signal Accelerators 82
3.5 Case Study: An Energy-Efficient Accelerator for Adaptive Dynamic Programming 94
4 Operational Principles and Learning in Spiking Neural Networks 119
4.1 Spiking Neural Networks 119
4.2 Learning in Shallow SNNs 124
4.3 Learning in Deep SNNs 146
5 Hardware Implementations of Spiking Neural Networks 173
5.1 The Need for Specialized Hardware 173
5.2 Digital SNNs 186
5.3 Analog/Mixed-Signal SNNs 210
6 Conclusions 247
A Appendix 257
Index 269
Скачать Learning in Energy-Efficient Neuromorphic Computing: Algorithm and Architecture Co-Design
|
Навигация
Вход на сайт
Реклама
Learning in Energy-Efficient Neuromorphic Computing: Algorithm and Architecture Co-Design 
