Limit search to available items
Book Cover
E-book
Author Prucnal, Paul R., author

Title Neuromorphic photonics / Paul R. Prucnal, Bhavin J. Shastri ; foreword by Malvin Carl Teich
Published Boca Raton : CRC Press, 2017

Copies

Description 1 online resource (445 pages)
Contents 1.1. Photonic Spike Processing -- 1.2. Technology Platforms for Neuromorphic Architectures -- 1.3. Challenges for Emerging Photonic Platforms -- 1.4. Brief History of Optics in Computing -- 1.4.1. Optical Logic -- 1.4.2. Optical Neural Networks -- 1.4.3. Optical Networks On-Chip -- 1.5. Application Domains -- 1.5.1. Real-Time Radio Frequency Processing -- 1.5.2. Nonlinear Programming -- 1.6. Organization of this Book -- 1.7. References -- 2.1. Introduction to Neural Networks -- 2.2. Spiking Neural Networks -- 2.3. Spiking Neuron Model -- 2.4. Excitability Mechanisms -- 2.5. References -- 3.1. Waveguides -- 3.1.1. Bends -- 3.1.2. Interwaveguide Couplers -- 3.1.3. Interferometers -- 3.1.4. Modulators -- 3.1.5. Multiplexing -- 3.2. Photodetectors -- 3.2.1. Photodiodes -- 3.2.2. Detection Noise -- 3.3. Optical Resonators -- 3.3.1. Microring Resonator Analysis -- 3.4. Lasers -- 3.4.1. Light-Matter Interaction -- 3.4.2. III-V Platforms -- 3.4.3. Laser Dynamics -- 3.5. References -- 4.1. SOA Based Photonic Neuromorphic Primitive -- 4.2. Lightwave Neuromorphic Circuits -- 4.2.1. Barn Owl Auditory Localization Algorithm -- 4.2.2. Crayfish Tail-Flip Escape Response -- 4.3. References -- 5.1. Introduction -- 5.2. Dynamical Model -- 5.3. Excitable Laser Systems -- 5.4. Results -- 5.4.1. Excitability -- 5.4.2. Temporal Pattern Recognition -- 5.4.3. Stable Recurrent Circuit -- 5.5. Discussion -- 5.6. Appendix -- 5.6.1. Fiber Laser Simulation -- 5.6.2. Integrated-Device Simulation -- 5.6.3. Excitable Fiber Ring Laser Cavity -- 5.7. References -- 6.1. Two-Section Gain and SA Excitable Laser -- 6.2. Semiconductor Ring and Microdisk Lasers -- 6.2.1. Semiconductor Ring Lasers -- 6.2.2. Microdisk Laser -- 6.3. Two-Dimensional Photonic Crystal Nanocavities -- 6.4. Resonant Tunneling Diode Photodetector and Laser Diode -- 6.5. Injection-Locked Semiconductor Lasers with Delayed Feedback -- 6.6. Semiconductor Lasers Subjected to Optical Feedback -- 6.7. Polarization Switching VCSELs -- 6.8. References -- 7.1. SOI Waveguides -- 7.2. Off-Chip Couplers -- 7.3. Modulators -- 7.4. Detectors -- 7.5. Hybrid Laser Sources -- 7.6. References -- 8.1. Broadcast-and-Weight Protocol -- 8.2. Processing-Network Node -- 8.2.1. WDM Weighted Addition -- 8.2.2. Total Power Detection -- 8.2.3. Nonlinear E/O Conversion -- 8.3. Broadcast Loop -- 8.4. Multiple Broadcast Loops -- 8.5. Discussion -- 8.6. Summary -- 8.7. References -- 9.1. Demonstration -- 9.2. Control of MRR Weight Banks -- 9.2.1. Setup and Methods -- 9.2.2. Single Channel Continuous Control -- 9.2.3. Multi-Channel Simultaneous Control -- 9.3. Coherent Effects Between MRR Channels -- 9.4. Quantitative Analysis for Photonic Weight Banks -- 9.4.1. Cross-Weight Power Penalty Metric -- 9.4.2. Weight Bank Channel Limits -- 9.5. Mathematical Description of WDM Weighting -- 9.6. Simulation Techniques for Tunable Waveguide Devices -- 9.6.1. Generalized Transmission Theory -- 9.6.2. Parametric Transmission Simulator -- 9.7. Appendix: Advanced Weight Bank Designs -- 9.8. Appendix: Basic Microring Characterization -- 9.8.1. Optical Characterization -- 9.8.2. Tuning Efficiency -- 9.8.3. Failure Characterization -- 9.8.4. Driver Design -- 9.9. References -- 10.1. Demonstration of a PNN -- 10.2. Theoretical Investigation of a PNN -- 10.2.1. Electronic Junction -- 10.2.2. Laser Neuron -- 10.2.3. Discussion -- 10.3. Other PNN formulations -- 10.3.1. Classification of O/E/O PNNs -- 10.3.2. Comparison of O/E/O and All-Optical PNNs -- 10.3.3. All-Optical PNNs -- 10.4. References -- 11.1. Broadcast-and-Weight Systems -- 11.1.1. Broadcast Topologies -- 11.1.2. Weight and Continue with Cascaded Banks -- 11.2. Weight bank control of time-delayed dynamics -- 11.3. A small photonic neural network -- 11.4. Multi-Broadcast Loop Systems -- 11.4.1. Generalized Interfacial PNN -- 11.4.2. The Multi-BL as an Embedded Graph -- 11.4.3. Mapping Multi-BL Embeddings to Functional Networks -- 11.4.4. Mapping Functional Networks to Multi-BL Embeddings -- 11.4.5. Design Example Using Nengo -- 11.4.6. Preliminary Structural Guidelines for General Systems -- 11.5. Fault Tolerance -- 11.6. References -- 12.1. Principal Component Analysis (PCA) -- 12.1.1. Mathematical Formulation of PCA -- 12.1.2. Oja's Rule -- 12.2. Independent Component Analysis (ICA) -- 12.2.1. Mathematical Formulation of ICA -- 12.3. Unsupervised Learning with STDP and IP -- 12.3.1. Synaptic Time Dependent Plasticity -- 12.3.2. Intrinsic Plasticity -- 12.3.3. Independent Component Analysis with STDP and IP -- 12.4. Experimental Advances on Photonic Learning Circuits -- 12.4.1. Photonic PCA -- 12.4.2. Photonic STDP -- 12.5. References -- 13.1. Reservoir Computing -- 13.1.1. Linear classifiers and reservoirs -- 13.1.2. Network-based reservoir computing -- 13.1.3. Delay-Based Reservoir Computing -- 13.2. Photonic Reservoir Computing -- 13.2.1. Reservoir Computing with a Single Dynamical Node -- 13.2.2. Reservoir Computing with a Silicon Photonics Chip -- 13.3. Discussion -- 13.4. References -- 14.1. Introduction -- 14.2. Technology Comparison -- 14.2.1. Electronic and Photonic Neurohardware Architectures -- 14.2.2. Speed: Bandwidth and Latency -- 14.2.3. Power Consumption: Energy and Noise -- 14.2.4. Size: Device Density and Scalability -- 14.2.5. Networking: Channel and Topology Limit -- 14.3. References
Summary "As societys appetite for information continues to grow, so does our need to process this information with increasing speed and versatility. Conventional one-size-fits-all solutions offered by digital electronics can no longer satisfy this need, as Moores law, interconnection density, and the von Neumann architecture reach their limits. These limitations are already being felt in advanced applications such as cognitive radio, adaptive control, and scientific computing. With its superior speed and reconfigurability, analog photonics can provide some relief to these problems; however, complex applications of analog photonics have remained largely unexplored due to the absence of a robust photonic integration industry. Recently, the landscape for commercially-manufacturable photonic chips has been changing rapidly and now promises to achieve economies of scale previously enjoyed solely by microelectronics. Despite the advent of commercially-viable photonic integration platforms, significant challenges still remain before scalable analog photonic processors can be realized. A central challenge is the development of mathematical bridges linking photonic device physics to models of complex analog information processing. Among such models, those of neural networks are perhaps the most widely studied and used by engineering communities. This book sets out to build bridges between the domains of photonic device physics and neural networks, providing a comprehensive overview of the emerging field of "neuromorphic photonics." It includes a thorough discussion of evolution of neuromorphic photonics from the advent of fiber-optic neurons to todays state-of-the-art integrated laser neurons, which are a current focus of international research. Neuromorphic Photonics explores candidate interconnection architectures and devices for integrated neuromorphic networks, along with key functionality such as learning. It is written at a level accessible to graduate students, while also intending to serve as a comprehensive reference for experts in the field."--Provided by publisher
Bibliography Includes bibliographical references and index
Notes Print version record
Subject Photonics.
Neural networks (Computer science)
Neural networks (Computer science)
Photonics
Genre/Form Handbooks and manuals.
Form Electronic book
Author Shastri, Bhavin J
ISBN 9781498725248
1498725244
9781351987615
1351987615
9781351987622
1351987623
9781351987608
1351987607
9781315370590
131537059X