Neuro-inspired computing using resistive synaptic devices

This book summarizes the recent breakthroughs in hardware implementation of neuro-inspired computing using resistive synaptic devices. The authors describe how two-terminal solid-state resistive memories can emulate synaptic weights in a neural network. Readers will benefit from state-of-the-art sum...

Full description

Saved in:
Bibliographic Details
Other Authors: Yu, Shimeng (Electrical engineer), (Editor)
Format: eBook
Language: English
Published: Cham, Switzerland : Springer, 2017.
Subjects:
ISBN: 9783319543130
9783319543123
Physical Description: 1 online resource (xi, 269 pages) : illustrations (some color)

Cover

Table of contents

LEADER 06308cam a2200433Ii 4500
001 100035
003 CZ-ZlUTB
005 20201229193814.0
006 m o d
007 cr cnu|||unuuu
008 170426s2017 sz a ob 000 0 eng d
040 |a N$T  |b eng  |e rda  |e pn  |c N$T  |d GW5XE  |d N$T  |d EBLCP  |d YDX  |d AZU  |d UPM  |d OCLCF  |d VT2  |d UAB  |d MERER  |d ESU  |d OCLCQ  |d IOG  |d OCLCQ  |d U3W  |d CAUOI  |d KSU  |d AU@  |d WYU  |d OCLCQ  |d AUD  |d OCLCQ  |d UKMGB  |d ERF  |d UKBTH  |d LEATE  |d OCLCQ 
020 |a 9783319543130  |q (electronic bk.) 
020 |z 9783319543123  |q (print) 
024 7 |a 10.1007/978-3-319-54313-0  |2 doi 
035 |a (OCoLC)984342561  |z (OCoLC)984340611  |z (OCoLC)984543009  |z (OCoLC)985215369  |z (OCoLC)985388618  |z (OCoLC)985504520  |z (OCoLC)985697129  |z (OCoLC)985948609  |z (OCoLC)986159395  |z (OCoLC)986270594  |z (OCoLC)986651343  |z (OCoLC)986807462  |z (OCoLC)988381647  |z (OCoLC)999487999  |z (OCoLC)1005801632  |z (OCoLC)1011792331  |z (OCoLC)1036295243  |z (OCoLC)1048172139  |z (OCoLC)1058336401  |z (OCoLC)1066499493  |z (OCoLC)1086541442  |z (OCoLC)1112595633  |z (OCoLC)1112864691  |z (OCoLC)1113592303  |z (OCoLC)1117222668  |z (OCoLC)1122810145  |z (OCoLC)1127184487 
245 0 0 |a Neuro-inspired computing using resistive synaptic devices /  |c Shimeng Yu, editor. 
264 1 |a Cham, Switzerland :  |b Springer,  |c 2017. 
300 |a 1 online resource (xi, 269 pages) :  |b illustrations (some color) 
336 |a text  |b txt  |2 rdacontent 
337 |a počítač  |b c  |2 rdamedia 
338 |a online zdroj  |b cr  |2 rdacarrier 
505 0 |a Preface; Acknowledgments; Contents; About the Editor; Chapter 1: Introduction to Neuro-Inspired Computing Using Resistive Synaptic Devices; 1.1 The Demand for New Hardware Beyond von Neumann Architecture; 1.2 Neuromorphic Hardware Accelerators and Why Resistive Synaptic Devices?; 1.3 Desirable Characteristics of Resistive Synaptic Devices; 1.4 Crossbar Array Architecture for Accelerating Weighted Sum and Weight Update; 1.5 Challenges of Mapping Learning Algorithms to Neuromorphic Hardware; References; Part I: Device-Level Demonstrations of Resistive Synaptic Devices. 
505 8 |a Chapter 2: Synaptic Devices Based on Phase-Change Memory2.1 PCM Basics for Synaptic Devices; 2.1.1 Device Operation; 2.1.2 Phase-Change Materials; 2.1.3 Threshold Switching Mechanism; 2.1.4 Resistance Drift; 2.1.5 Scaling; 2.1.6 Array Architecture and Memory Cell Selector; 2.1.7 Power Consumption; 2.2 PCM Synaptic Device Implementations; 2.2.1 PCM as an Electronic Synapse; 2.2.2 Synaptic Plasticity and Learning; 2.2.3 Pulse Schemes for Plasticity; 2.2.4 Gradual Programming Versus Stochastic Programming; 2.3 Future Outlook; 2.3.1 Resistance State Stability; 2.3.2 New Materials Exploration. 
505 8 |a 2.3.3 Ovonic Threshold SwitchReferences; Chapter 3: Pr0.7Ca0.3MnO3 (PCMO)-Based Synaptic Devices; 3.1 Nanoscale PCMO-Based Synaptic Device; 3.2 Reactive Electrode Dependence of PCMO-Based Synaptic Device; 3.3 Nitrogen Treatment for Tunable Synaptic Characteristics; 3.4 Approaches to Improve Synaptic Characteristics; 3.5 Summary and Outlook; References; Chapter 4: TaOx-/TiO2-Based Synaptic Devices; 4.1 Device Fabrication Method; 4.2 Basic Device Characteristics; 4.3 Switching Mechanism; 4.3.1 Experimental Findings; 4.3.2 Physical Modeling; 4.4 Synaptic Function Realization and Modeling Results. 
505 8 |a 4.4.1 Potentiation and Depression4.4.2 Spike-Timing-Dependent Plasticity; 4.4.3 Paired-Pulse Facilitation; 4.5 3D Synaptic Network; 4.5.1 3D Synaptic Network Realization; 4.5.2 Linearity Tuning; 4.6 Summary and Outlook; References; Part II: Array-Level Demonstrations of Resistive Synaptic Devices and Neural Networks; Chapter 5: Training and Inference in Hopfield Network Using 10x10 Phase Change Synaptic Array; 5.1 Introduction; 5.2 Phase Change Memory Array for Synaptic Operation; 5.3 Hebbian Learning in Synaptic Array. 
505 8 |a 5.4 Effects of Device-to-Device Variation on Associative Learning Performance5.5 Summary; References; Chapter 6: Experimental Demonstration of Firing Rate Neural Networks Based on Metal-Oxide Memristive Crossbars; 6.1 Introduction; 6.2 Memristive Devices and Crossbar Circuits; 6.2.1 Device Fabrication and Forming; 6.2.2 Dynamic Characteristics; 6.3 Single-Layer Perceptron; 6.3.1 Inference; 6.3.2 Network Training; 6.4 Multilayer Perceptron; 6.5 3D Memristor-CMOS Hybrid Circuits; 6.6 Challenges and Future Work; References. 
506 |a Plný text je dostupný pouze z IP adres počítačů Univerzity Tomáše Bati ve Zlíně nebo vzdáleným přístupem pro zaměstnance a studenty 
520 |a This book summarizes the recent breakthroughs in hardware implementation of neuro-inspired computing using resistive synaptic devices. The authors describe how two-terminal solid-state resistive memories can emulate synaptic weights in a neural network. Readers will benefit from state-of-the-art summaries of resistive synaptic devices, from the individual cell characteristics to the large-scale array integration. This book also discusses peripheral neuron circuits design challenges and design strategies. Finally, the authors describe the impact of device non-ideal properties (e.g. noise, variation, yield) and their impact on the learning performance at the system-level, using a device-algorithm co-design methodology." Provides single-source reference to recent breakthroughs in resistive synaptic devices, not only at individual cell-level, but also at integrated array-level; " Includes detailed discussion of the peripheral circuits and array architecture design of the neuro-crossbar system; " Focuses on new experimental results that are likely to solve practical, artificial intelligent problems, such as image classification. 
504 |a Includes bibliographical references at the end of each chapters. 
590 |a SpringerLink  |b Springer Complete eBooks 
650 0 |a Neural computers. 
655 7 |a elektronické knihy  |7 fd186907  |2 czenas 
655 9 |a electronic books  |2 eczenas 
700 1 |a Yu, Shimeng  |c (Electrical engineer),  |e editor. 
776 0 8 |i Print version:  |t Neuro-inspired computing using resistive synaptic devices.  |d Cham, Switzerland : Springer, 2017  |z 9783319543123  |z 3319543121  |w (OCoLC)970684214 
856 4 0 |u https://proxy.k.utb.cz/login?url=https://link.springer.com/10.1007/978-3-319-54313-0  |y Plný text 
992 |c NTK-SpringerENG 
999 |c 100035  |d 100035