Energy-Efficient Devices and Circuits for Neuromorphic Computing

Farooq Ahmad Khanday

• Publisher: Elsevier
• Year: 2025
• Topic: Computer Science
• eBook ISBN:
  9780443299827
• Subtopic: Computer Science General
• Index: Computer Science

Energy-Efficient Devices and Circuits for Neuromorphic Computing is an important contribution to this field, covering topics from neuron dynamics to energy-efficient CMOS devices and circuits. The book delves into theoretical analysis of learning processes in spiking neural networks, two-terminal neuromorphic devices, material-engineered neuromorphic devices, and novel biomimetic Si devices. It offers insights into the latest developments in non-volatile memory crossbar arrays and emerging post-CMOS devices. Overall, it provides a comprehensive overview of energy-efficient neuromorphic computing architecture. This book is an essential resource for researchers, engineers, and students working in neuromorphic computing and energy-efficient electronics. - Provides comprehensive coverage of neuromorphic computing based upon energy-efficient electronic devices and circuits - Presents practical guidance and numerous examples, making it an excellent resource for researchers, engineers, and students designing energy-efficient neuromorphic computing systems - Includes detailed coverage of emerging post-CMOS devices such as memristors and MTJs and their potential applications in energy-efficient synapses and neurons

Table of contents

• Cover image
• Title page
• Copyright
• Dedication
• Contents
• Contributors
• Editor Biography
• Foreword
• Preface
• Acknowledgments
• CHAPTER 1 Spiking neural networks: Mathematical models, learning algorithms, and applications
• CHAPTER 2 Artificial spiking neuron architectures: Devices and circuits for neuromorphic computing
• CHAPTER 3 The novel energy-efficient neuromorphic computing devices
• CHAPTER 4 Memristive spiking neurons for neuromorphic applications
• CHAPTER 5 Memristor-driven neuromorphic computing with crossbar arrays: A hardware perspective
• CHAPTER 6 Current-controlled memristive synapse for optimized and energy-efficient neuroprocessor
• CHAPTER 7 Circuit-level compensation techniques to reduce power in resistive memory arrays for neuromorphic computing
• CHAPTER 8 In-sensor computing: A comprehensive review
• CHAPTER 9 Low-power 3-D IC-based spiking neural network
• CHAPTER 10 Achieving energy efficiency in FPGA-based neural network inference accelerators through approximate computing
• CHAPTER 11 SENECA project: An effort to make a low-power digital neuromorphic processor
• CHAPTER 12 Neuromorphic computing for traffic prediction in networks-on-chip
• CHAPTER 13 Transforming AI landscape with neuromorphic computing and chiplets
• CHAPTER 14 Exploring the realms of echo state networks
• Index