Photonic Neural Networks with Spatiotemporal Dynamics : : Paradigms of Computing and Implementation.
Saved in:
: | |
---|---|
TeilnehmendeR: | |
Place / Publishing House: | Singapore : : Springer,, 2023. ©2024. |
Year of Publication: | 2023 |
Edition: | 1st ed. |
Language: | English |
Online Access: | |
Physical Description: | 1 online resource (277 pages) |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 08119nam a22004333i 4500 | ||
---|---|---|---|
001 | 50030882937 | ||
003 | MiAaPQ | ||
005 | 20240229073851.0 | ||
006 | m o d | | ||
007 | cr cnu|||||||| | ||
008 | 240229s2023 xx o ||||0 eng d | ||
020 | |a 9789819950720 |q (electronic bk.) | ||
020 | |z 9789819950713 | ||
035 | |a (MiAaPQ)50030882937 | ||
035 | |a (Au-PeEL)EBL30882937 | ||
035 | |a (OCoLC)1409705951 | ||
040 | |a MiAaPQ |b eng |e rda |e pn |c MiAaPQ |d MiAaPQ | ||
050 | 4 | |a Q334-342 | |
100 | 1 | |a Suzuki, Hideyuki. | |
245 | 1 | 0 | |a Photonic Neural Networks with Spatiotemporal Dynamics : |b Paradigms of Computing and Implementation. |
250 | |a 1st ed. | ||
264 | 1 | |a Singapore : |b Springer, |c 2023. | |
264 | 4 | |c ©2024. | |
300 | |a 1 online resource (277 pages) | ||
336 | |a text |b txt |2 rdacontent | ||
337 | |a computer |b c |2 rdamedia | ||
338 | |a online resource |b cr |2 rdacarrier | ||
505 | 0 | |a Intro -- Preface -- Contents -- Introduction -- Revival of Optical Computing -- 1 Introduction -- 2 Fourier Optical Processing -- 3 Digital Optical Computing -- 4 Optical Neurocomputing -- 5 Optical Special Purpose Processing -- 6 Nanophotonic Computing -- 7 Toward Further Extension -- References -- Nonlinear Dynamics and Computing in Recurrent Neural Networks -- 1 Introduction -- 2 Fundamental RNN Models and Energy Function -- 2.1 Amari-Hopfield Network with Binary States -- 2.2 Amari-Hopfield Network with Continuous States -- 2.3 Boltzmann Machine -- 3 Nonlinear Dynamics in Symmetrically Connected RNNs -- 3.1 Chaotic Neural Network -- 3.2 Chaotic Boltzmann Machine -- 3.3 Ising Machines -- 3.4 Herding System -- 4 Reservoir Computing -- 4.1 Training Input-Output Relation of RNNs -- 4.2 Echo State Network -- 4.3 Echo State Property and Reservoir Design -- 4.4 Neural Network Reservoirs -- 4.5 Physical Reservoir Computing -- 5 Towards Photonic Neural Network Computing -- References -- Fluorescence Energy Transfer Computing -- Fluorescence Energy Transfer Computing -- 1 Fluorescence Energy Transfer -- 2 FRET-Based Device -- 2.1 DNA for FRET Devices -- 2.2 FRET-Based Photonic Wire -- 2.3 FRET-Based Photonic Switch -- 2.4 FRET-Based Logic Gate -- 3 Scaffold DNA Logic -- 3.1 Basic Concept -- 3.2 Arrangement Control of Fluorescent Molecules -- 3.3 Design of Logic Operations -- 3.4 AND Operation -- 3.5 OR Operation -- 3.6 NOT Operation -- 3.7 Extended FRET Connection -- 4 Optical Program of DNA Scaffold Logic -- 4.1 Optical Control of FRET -- 4.2 Optical Control of FRET Pathway -- 4.3 Optically Programmable DNA Scaffold Logic -- 5 FRET Network-Based Computation -- References -- Quantum-Dot-Based Photonic Reservoir Computing -- 1 Introduction -- 2 Quantum-Dot-Based Physical Reservoir -- 2.1 Basics -- 2.2 Experimental Demonstration: Randomly-Dispersed QDR. | |
505 | 8 | |a 2.3 Experimental Demonstration: Electrophoresis -- 3 Non-linearity of the QD Reservoir -- 3.1 Experimental Setup -- 3.2 Qualitative Non-linearity -- 4 Spatio-Temporal Photonic Processing -- 4.1 Basics -- 4.2 Streak Measurement -- 4.3 Spatiotemporal Reservoir Model -- 4.4 Experimental Demonstration -- 5 Conclusion and Future Prospect -- References -- Exploring Integrated Device Implementation for FRET-Based Optical Reservoir Computing -- 1 Introduction -- 2 Proposed Device Structure -- 2.1 Device Structure -- 2.2 Network Mapping -- 2.3 Experiments -- 3 Proof-of-Concept Prototyping -- 3.1 Implementation -- 3.2 Evaluation -- 4 Discussion on Energy Advantage -- 4.1 Power Estimation Approach -- 4.2 Result -- 5 Summary -- References -- FRET Networks: Modeling and Analysis for Computing -- 1 Introduction -- 2 Spatiotemporal Model for FRET Networks -- 2.1 Multiple-Donor Model -- 2.2 Analytical Results -- 3 Simulation Methods -- 3.1 Deterministic Simulation -- 3.2 Stochastic Simulation -- 3.3 Comparison Between Deterministic and Stochastic Simulation -- 4 Information Processing Using FRET Networks -- 4.1 Nonlinear Function Approximation -- 4.2 Chaotic Time-Series Prediction -- 4.3 Handwritten Digit Recognition -- 5 Conclusions and Future Works -- References -- Quantum Walk on FRET Networks -- 1 Introduction of Quantum Walk -- 1.1 Classical Random Walk -- 1.2 Quantum Walk -- 1.3 Quantum Walk on FRET Networks -- 2 Application of Quantum Walk -- 2.1 Classical Parton Shower -- 2.2 Quantum Parton Shower Algorithm -- 3 Conclusion -- References -- Spatial-Photonic Spin System -- Spatial Photonic Ising Machine with Time/Space Division Multiplexing -- 1 Introduction -- 2 Spatial Photonic Ising Machine with Multiplexing -- 2.1 Basic Scheme of SPIM -- 2.2 Concept of SPIMs with Multiplexing -- 3 Time Division Multiplexed (TDM)-SPIM. | |
505 | 8 | |a 4 Space Division Multiplexing (SDM)-SPIM -- 5 Conclusion -- References -- Investigation on Oscillator-Based Ising Machines -- 1 Introduction -- 2 Ising Model and Ising Machines -- 3 Oscillator-Based Ising Machines -- 3.1 Phase Oscillators -- 3.2 Second-Harmonic Injection Locking -- 3.3 Kuramoto Model -- 3.4 Gradient Structure of the Kuramoto Model -- 3.5 Working Principle of OIMs -- 4 Experiments -- 4.1 MAX-CUT Problem -- 4.2 Experimental Setting and Evaluation Metrics -- 4.3 Effect of Properties of Noisy Fluctuation and Coarse Time Discretization -- 4.4 Effect of Injection and Noise Strength -- 4.5 Effect of Higher Harmonics in Coupling and Injection Schemes -- 5 Summary -- References -- Sampling-Like Dynamics of the Nonlinear Dynamical System Combined with Optimization -- 1 Herding: Sample Generation Using Nonlinear Dynamics and Monte Carlo Integration -- 1.1 Deterministic Tossup -- 1.2 Herding -- 1.3 Convergence of Herding -- 2 Herded Gibbs: Model-Based Herding on Spin System -- 2.1 Markov Chain Monte Carlo Method -- 2.2 Herded Gibbs -- 2.3 Sharing Weight Variables -- 2.4 Monte Carlo Integration Using HG -- 2.5 Rao-Blackwellization -- 3 Entropic Herding: Regularizer for Dynamical Sampling -- 3.1 Maximum Entropy Principle -- 3.2 Entropic Herding -- 3.3 Dynamical Entropic Maximization in Herding -- 3.4 Other Notes on Entropic Herding -- 4 Discussion -- 4.1 Application of Physical Combinatorial Optimization Using Herding -- 4.2 Generative Models and Herding -- 5 Conclusion -- References -- Photonic Reservoir Computing -- Reservoir Computing Based on Iterative Function Systems -- 1 Introduction -- 2 Iterative Function Systems -- 3 Iterative Function System-Based Reservoir Computing -- 4 Prediction Performance of IFSRC -- 4.1 Multi-step Ahead Prediction -- 4.2 Single-Step Ahead Prediction of Santa Fe Time-Series Data. | |
505 | 8 | |a 5 Experimental Performance of IFS Reservoir Computing -- 5.1 Optical Setup -- 5.2 Multi-step Ahead Prediction of Mackey-Glass Equation -- 5.3 Single-step Ahead Prediction of Santa Fe Time-Series Data -- 6 Relationship Between Performance and Spectral Radius -- 7 IFS Reservoir Computing with Optical Feedback Loop -- 8 Discussion -- References -- Bridging the Gap Between Reservoirs and Neural Networks -- 1 Introduction -- 2 Background -- 2.1 Lottery Ticket Hypotheses -- 2.2 Residual Neural Networks -- 3 Hidden-Fold Networks -- 3.1 Folded ResNet Architecture -- 3.2 Supermask Training -- 4 Experiments and Results -- 4.1 Experimental Settings -- 4.2 Results -- 5 Summary -- References -- Brain-Inspired Reservoir Computing Models -- 1 Introduction -- 2 Reservoir-Based Predictive Coding Model -- 3 Reservoir-Based Reinforcement Learning Model -- 4 Integrated Model and Mental simulation -- 5 Summary -- References. | |
588 | |a Description based on publisher supplied metadata and other sources. | ||
590 | |a Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries. | ||
655 | 4 | |a Electronic books. | |
700 | 1 | |a Tanida, Jun. | |
700 | 1 | |a Hashimoto, Masanori. | |
776 | 0 | 8 | |i Print version: |a Suzuki, Hideyuki |t Photonic Neural Networks with Spatiotemporal Dynamics |d Singapore : Springer,c2023 |z 9789819950713 |
797 | 2 | |a ProQuest (Firm) | |
856 | 4 | 0 | |u https://ebookcentral.proquest.com/lib/oeawat/detail.action?docID=30882937 |z Click to View |