Photonic Reservoir Computing : : Optical Recurrent Neural Networks / / ed. by Daniel Brunner, Guy Van der Sande, Miguel C. Soriano.
Photonics has long been considered an attractive substrate for next generation implementations of machine-learning concepts. Reservoir Computing tremendously facilitated the realization of recurrent neural networks in analogue hardware. This concept exploits the properties of complex nonlinear dynam...
Saved in:
Superior document: | Title is part of eBook package: De Gruyter DG Plus eBook-Package 2019 |
---|---|
MitwirkendeR: | |
HerausgeberIn: | |
Place / Publishing House: | Berlin ;, Boston : : De Gruyter, , [2019] ©2019 |
Year of Publication: | 2019 |
Language: | English |
Online Access: | |
Physical Description: | 1 online resource (XIII, 264 p.) |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- Frontmatter
- Preface
- Contents
- List of Contributing Authors
- 1. Introduction to novel photonic computing
- 2. Information processing and computation with photonic reservoir systems
- 3. Integrated on-chip reservoirs
- 4. Large scale spatiotemporal reservoirs
- 5. Time delay systems for reservoir computing
- 6. Ikeda delay dynamics as Reservoir processors
- 7. Semiconductor lasers as reservoir substrates
- 8. Advanced reservoir computers: analogue autonomous systems and real time control
- Outlook
- Index