Event-Based Neuromorphic Systems (eBook, PDF)

Redaktion: Liu, Shih-Chii; Douglas, Rodney; Whatley, Adrian; Indiveri, Giacomo; Delbruck, Tobi

• Format: PDF

Produktbeschreibung

Neuromorphic electronic engineering takes its inspiration from the functioning of nervous systems to build more power efficient electronic sensors and processors. Event-based neuromorphic systems are inspired by the brain's efficient data-driven communication design, which is key to its quick responses and remarkable capabilities. This cross-disciplinary text establishes how circuit building blocks are combined in architectures to construct complete systems. These include vision and auditory sensors as well as neuronal processing and learning circuits that implement models of nervous systems. Techniques for building multi-chip scalable systems are considered throughout the book, including methods for dealing with transistor mismatch, extensive discussions of communication and interfacing, and making systems that operate in the real world. The book also provides historical context that helps relate the architectures and circuits to each other and that guides readers to the extensive literature. Chapters are written by founding experts and have been extensively edited for overall coherence. This pioneering text is an indispensable resource for practicing neuromorphic electronic engineers, advanced electrical engineering and computer science students and researchers interested in neuromorphic systems. Key features: * Summarises the latest design approaches, applications, and future challenges in the field of neuromorphic engineering. * Presents examples of practical applications of neuromorphic design principles. * Covers address-event communication, retinas, cochleas, locomotion, learning theory, neurons, synapses, floating gate circuits, hardware and software infrastructure, algorithms, and future challenges.

---

Dieser Download kann aus rechtlichen Gründen nur mit Rechnungsadresse in A, B, BG, CY, CZ, D, DK, EW, E, FIN, F, GR, HR, H, IRL, I, LT, L, LR, M, NL, PL, P, R, S, SLO, SK ausgeliefert werden.

Produktdetails

• Verlag: Wiley-Scrivener
• Seitenzahl: 440
• Erscheinungstermin: 23. Dezember 2014
• Englisch
• ISBN-13: 9781118927632
• Artikelnr.: 42088023

Autorenporträt

Shih-Chii Liu is a group leader at the Institute of Neuroinformatics, University of Zurich and ETH Zurich.  She received her Ph.D. in the Computation and Neural Systems program at Caltech. She has been an instructor and topic organizer at the NSF Telluride Neuromorphic Cognition Engineering Workshop in Telluride, Colorado since 1998. She has also co-authored a book on analog VLSI circuits (published by MIT Press), is an IEEE Senior member and has held offices in a number of scientific and IEEE engineering international conferences. Dr Liu has been working on event-based vision and auditory sensors, multi-neuron networks, and asynchronous circuits for more than 20 years. Tobi Delbruck has been Professor of Physics and Electrical Engineering at the Institute of Neuroinformatics since 1998. He leads the Sensors group which focuses on neuromorphic sensors and processing. He received his Ph.D. in the Computation and Neural Systems program at Caltech.  He worked on electronic imaging at Arithmos, Synaptics, National Semiconductor, and Foveon. He co-organized the Telluride Neuromorphic Cognition Engineering summer workshop and the live demonstration sessions at ISCAS and NIPS, and is former chair of the IEEE CAS Sensory Systems Technical Committee. He has been awarded 9 IEEE awards and is an IEEE Fellow. Giacomo Indiveri is a Professor at the University of Zurich's Faculty of Science. He obtained his M.Sc. degree in Electrical Engineering and his Ph.D. degree in Computer Science from the University of Genoa, Italy. He is an ERC fellow and an IEEE Senior member. His research interests lie in the study of real and artificial neural processing systems, and in the hardware implementation of neuromorphic cognitive systems, using full custom analog and digital VLSI technology. Adrian M. Whatley gained a degree in Chemistry at the University of Bristol in England in 1986. After working for 10 years in the British computer industry, he took up his current software engineering position at the Institute of Neuroinformatics where he works primarily on asynchronous Address-Event communication systems. Rodney Douglas is a co-founder of the Institute of Neuroinformatics. His central research interest over the past 25 years has been the nature of computation by the circuits of the neocortex and their implementation both in software simulation, in custom electronic hardware. The experimental aspect of his work has inspired a number of cortical models of processing that use recurrently connected neuronal architectures.  He is currently exploring principles of self-assembly in simple organisms and circuits which he considers crucial for building truly autonomous neuromorphic cognitive systems.

Inhaltsangabe

List of Contributors xv
Foreword xvii
Acknowledgments xix
List of Abbreviations and Acronyms xxi
1 Introduction 1
1.1 Origins and Historical Context 3
1.2 Building Useful Neuromorphic Systems 5
References 5
Part I UNDERSTANDING NEUROMORPHIC SYSTEMS 7
2 Communication 9
2.1 Introduction 9
2.2 Address-Event Representation 12
2.2.1 AER Encoders 13
2.2.2 Arbitration Mechanisms 13
2.2.3 Encoding Mechanisms 17
2.2.4 Multiple AER Endpoints 19
2.2.5 Address Mapping 19
2.2.6 Routing 19
2.3 Considerations for AER Link Design 20
2.3.1 Trade-off: Dynamic or Static Allocation 21
2.3.2 Trade-off: Arbitered Access or Collisions? 23
2.3.3 Trade-off: Queueing versus Dropping Spikes 24
2.3.4 Predicting Throughput Requirements 25
2.3.5 Design Trade-offs 27
2.4 The Evolution of AER Links 28
2.4.1 Single Sender, Single Receiver 28
2.4.2 Multiple Senders, Multiple Receivers 30
2.4.3 Parallel Signal Protocol 31
2.4.4 Word-Serial Addressing 32
2.4.5 Serial Differential Signaling 33
2.5 Discussion 34
References 35
3 Silicon Retinas 37
3.1 Introduction 37
3.2 Biological Retinas 38
3.3 Silicon Retinas with Serial Analog Output 39
3.4 Asynchronous Event-Based Pixel Output Versus Synchronous Frames 40
3.5 AER Retinas 40
3.5.1 Dynamic Vision Sensor 41
3.5.2 Asynchronous Time-Based Image Sensor 46
3.5.3 Asynchronous Parvo-Magno Retina Model 46
3.5.4 Event-Based Intensity-Coding Imagers (Octopus and TTFS) 48
3.5.5 Spatial Contrast and Orientation Vision Sensor (VISe) 50
3.6 Silicon Retina Pixels 54
3.6.1 DVS Pixel 54
3.6.2 ATIS Pixel 56
3.6.3 VISe Pixel 58
3.6.4 Octopus Pixel 59
3.7 New Specifications for Silicon Retinas 60
3.7.1 DVS Response Uniformity 60
3.7.2 DVS Background Activity 62
3.7.3 DVS Dynamic Range 62
3.7.4 DVS Latency and Jitter 63
3.8 Discussion 64
References 67
4 Silicon Cochleas 71
4.1 Introduction 72
4.2 Cochlea Architectures 75
4.2.1 Cascaded 1D 76
4.2.2 Basic 1D Silicon Cochlea 77
4.2.3 2D Architecture 78
4.2.4 The Resistive (Conductive) Network 79
4.2.5 The BM Resonators 80
4.2.6 The 2D Silicon Cochlea Model 80
4.2.7 Adding the Active Nonlinear Behavior of the OHCs 82
4.3 Spike-Based Cochleas 83
4.3.1 Q-control of AEREAR2 Filters 85
4.3.2 Applications: Spike-Based Auditory Processing 86
4.4 Tree Diagram 87
4.5 Discussion 87
References 89
5 Locomotion Motor Control 91
5.1 Introduction 92
5.1.1 Determining Functional Biological Elements 92
5.1.2 Rhythmic Motor Patterns 93
5.2 Modeling Neural Circuits in Locomotor Control 95
5.2.1 Describing Locomotor Behavior 96
5.2.2 Fictive Analysis 97
5.2.3 Connection Models 99
5.2.4 Basic CPG Construction 100
5.2.5 Neuromorphic Architectures 102
5.3 Neuromorphic CPGs at Work 108
5.3.1 A Neuroprosthesis: Control of Locomotion in Vivo 109
5.3.2 Walking Robots 111
5.3.3 Modeling Intersegmental Coordination 112
5.4 Discussion 113
References 115
6 Learning in Neuromorphic Systems 119
6.1 Introduction: Synaptic Connections, Memory, and Learning 120
6.2 Retaining Memories in Neuromorphic Hardware 121
6.2.1 The Problem of Memory Maintenance: Intuition 121
6.2.2 The Problem of Memory Maintenance: Quantitative Analysis 122
6.2.3 Solving the Problem of Memory Maintenance 124
6.3 Storing Memories in Neuromorphic Hardware 128
6.3.1 Synaptic Models for Learning 128
6.3.2 Implementing a Synaptic Model in Neuromorphic Hardware 132
6.4 Toward Associative Memories in Neuromorphic Hardware 136
6.4.1 Memory Retrieval in Attractor Neural Networks 137
6.4.2 Issues 142
6.5 Attractor States in a Neuromorphic Chip 143
6.5.1 Memory Retrieval 143
6.5.2 Learning Visual Stimuli in Real Time 145
6.6 Discussion 148
References 149
Part II BUILDING NEUROMORPHIC SYSTEMS 153
7 Silicon Neurons 155
7.1 Introduction 156
7.2 Silicon Neuron Circuit Blocks 158
7.2.1 Conductance Dynamics 158
7.2.2 Spike-Event Generation 159
7.2.3 Spiking Thresholds and Refractory Periods 161
7.2.4 Spike-Frequency Adaptation and Adaptive Thresholds 162
7.2.5 Axons and Dendritic Trees 164
7.2.6 Additional Useful Building Blocks 165
7.3 Silicon Neuron Implementations 166
7.3.1 Subthreshold Biophysically Realistic Models 166
7.3.2 Compact I&F Circuits for Event-Based Systems 169
7.3.3 Generalized I&F Neuron Circuits 170
7.3.4 Above Threshold, Accelerated-Time, and Switched-Capacitor Designs 174
7.4 Discussion 176
References 180
8 Silicon Synapses 185
8.1 Introduction 186
8.2 Silicon Synapse Implementations 188
8.2.1 Non Conductance-Based Circuits 188
8.2.2 Conductance-Based Circuits 198
8.2.3 NMDA Synapse 200
8.3 Dynamic Plastic Synapses 201
8.3.1 Short-Term Plasticity 201
8.3.2 Long-Term Plasticity 203
8.4 Discussion 213
References 215
9 Silicon Cochlea Building Blocks 219
9.1 Introduction 219
9.2 Voltage-Domain Second-Order Filter 220
9.2.1 Transconductance Amplifier 220
9.2.2 Second-Order Low-Pass Filter 222
9.2.3 Stability of the Filter 223
9.2.4 Stabilised Second-Order Low-Pass Filter 225
9.2.5 Differentiation 225
9.3 Current-Domain Second-Order Filter 227
9.3.1 The Translinear Loop 227
9.3.2 Second-Order Tau Cell Log-Domain Filter 229
9.4 Exponential Bias Generation 230
9.5 The Inner Hair Cell Model 233
9.6 Discussion 234
References 234
10 Programmable and Configurable Analog Neuromorphic ICs 237
10.1 Introduction 238
10.2 Floating-Gate Circuit Basics 238
10.3 Floating-Gate Circuits Enabling Capacitive Circuits 238
10.4 Modifying Floating-Gate Charge 242
10.4.1 Electron Tunneling 242
10.4.2 pFET Hot-Electron Injection 242
10.5 Accurate Programming of Programmable Analog Devices 244
10.6 Scaling of Programmable Analog Approaches 246
10.7 Low-Power Analog Signal Processing 247
10.8 Low-Power Comparisons to Digital Approaches: Analog Computing in
Memory 249
10.9 Analog Programming at Digital Complexity: Large-Scale Field
Programmable Analog Arrays 251
10.10 Applications of Complex Analog Signal Processing 253
10.10.1 Analog Transform Imagers 253
10.10.2 Adaptive Filters and Classifiers 253
10.11 Discussion 256
References 257
11 Bias Generator Circuits 261
11.1 Introduction 261
11.2 Bias Generator Circuits 263
11.2.1 Bootstrapped Current Mirror Master Bias Current Reference 263
11.2.2 Master Bias Power Supply Rejection Ratio (PSRR) 265
11.2.3 Stability of the Master Bias 265
11.2.4 Master Bias Startup and Power Control 266
11.2.5 Current Splitters: Obtaining a Digitally Controlled Fraction of the
Master Current 267
11.2.6 Achieving Fine Monotonic Resolution of Bias Currents 271
11.2.7 Using Coarse-Fine Range Selection 273
11.2.8 Shifted-Source Biasing for Small Currents 274
11.2.9 Buffering and Bypass Decoupling of Individual Biases 275
11.2.10 A General Purpose Bias Buffer Circuit 278
11.2.11 Protecting Bias Splitter Currents from Parasitic Photocurrents 279
11.3 Overall Bias Generator Architecture Including External Controller 279
11.4 Typical Characteristics 280
11.5 Design Kits 281
11.6 Discussion 282
References 282
12 On-Chip AER Communication Circuits 285
12.1 Introduction 286
12.1.1 Communication Cycle 286
12.1.2 Speedup in Communication 287
12.2 AER Transmitter Blocks 289
12.2.1 AER Circuits within a Pixel 289
12.2.2 Arbiter 290
12.2.3 Other AER Blocks 295
12.2.4 Combined Operation 297
12.3 AER Receiver Blocks 298
12.3.1 Chip-Level Handshaking Block 298
12.3.2 Decoder 299
12.3.3 Handshaking Circuits in Receiver Pixel 300
12.3.4 Pulse Extender Circuits 301
12.3.5 Receiver Array Peripheral Handshaking Circuits 301
12.4 Discussion 302
References 303
13 Hardware Infrastructure 305
13.1 Introduction 306
13.1.1 Monitoring AER Events 307
13.1.2 Sequencing AER Events 311
13.1.3 Mapping AER Events 313
13.2 Hardware Infrastructure Boards for Small Systems 316
13.2.1 Silicon Cortex 316
13.2.2 Centralized Communication 317
13.2.3 Composable Architecture Solution 318
13.2.4 Daisy-Chain Architecture 324
13.2.5 Interfacing Boards using Serial AER 324
13.2.6 Reconfigurable Mesh-Grid Architecture 328
13.3 Medium-Scale Multichip Systems 329
13.3.1 Octopus Retina + IFAT 329
13.3.2 Multichip Orientation System 332
13.3.3 CAVIAR 335
13.4 FPGAs 340
13.5 Discussion 342
References 345
14 Software Infrastructure 349
14.1 Introduction 349
14.1.1 Importance of Cross-Community Commonality 350
14.2 Chip and System Description Software 350
14.2.1 Extensible Markup Language 351
14.2.2 NeuroML 351
14.3 Configuration Software 352
14.4 Address Event Stream Handling Software 352
14.4.1 Field-Programmable Gate Arrays 353
14.4.2 Structure of AE Stream Handling Software 353
14.4.3 Bandwidth and Latency 353
14.4.4 Optimization 354
14.4.5 Application Programming Interface 355
14.4.6 Network Transport of AE Streams 355
14.5 Mapping Software 356
14.6 Software Examples 357
14.6.1 ChipDatabase - A System for Tuning Neuromorphic aVLSI Chips 357
14.6.2 Spike Toolbox 359
14.6.3 jAER 359
14.6.4 Python and PyNN 360
14.7 Discussion 363
References 363
15 Algorithmic Processing of Event Streams 365
15.1 Introduction 365
15.2 Requirements for Software Infrastructure 367
15.2.1 Processing Latency 369
15.3 Embedded Implementations 369
15.4 Examples of Algorithms 370
15.4.1 Noise Reduction Filters 370
15.4.2 Time-Stamp Maps and Subsampling by Bit-Shifting Addresses 372
15.4.3 Event Labelers as Low-Level Feature Detectors 372
15.4.4 Visual Trackers 374
15.4.5 Event-Based Audio Processing 378
15.5 Discussion 379
References 379
16 Towards Large-Scale Neuromorphic Systems 381
16.1 Introduction 381
16.2 Large-Scale System Examples 382
16.2.1 Spiking Neural Network Architecture 382
16.2.2 Hierarchical AER 384
16.2.3 Neurogrid 386
16.2.4 High Input Count Analog Neural Network System 388
16.3 Discussion 390
References 391
17 The Brain as Potential Technology 393
17.1 Introduction 393
17.2 The Nature of Neuronal Computation: Principles of Brain Technology 395
17.3 Approaches to Understanding Brains 396
17.4 Some Principles of Brain Construction and Function 398
17.5 An Example Model of Neural Circuit Processing 400
17.6 Toward Neuromorphic Cognition 402
References 404
Index 407