This book, the first of its kind, bridges the gap between the increasingly interlinked fields of nanophotonics and artificial intelligence (AI). While artificial intelligence techniques, machine learning in particular, have revolutionized many different areas of scientific research, nanophotonics holds a special position as it simultaneously benefits from AI-assisted device design whilst providing novel computing platforms for AI. This book is aimed at both researchers in nanophotonics who want to utilize AI techniques and researchers in the computing community in search of new photonics-based hardware. The book guides the reader through the general concepts and specific topics of relevance from both nanophotonics and AI, including optical antennas, metamaterials, metasurfaces, and other photonic devices on the one hand, and different machine learning paradigms and deep learning algorithms on the other. It goes on to comprehensively survey inverse techniques for device design, AI-enabled applications in nanophotonics, and nanophotonic platforms for AI. This book will be essential reading for graduate students, academic researchers, and industry professionals from either side of this fast-developing, interdisciplinary field.
Author(s): Kan Yao, Yuebing Zheng
Series: Springer Series in Optical Sciences, 241
Publisher: Springer
Year: 2023
Language: English
Pages: 187
City: Cham
Preface
Contents
Chapter 1: Fundamentals of Nanophotonics
1.1 Plasmonics and Surface Plasmons
1.1.1 Surface Plasmon Polaritons
1.1.2 Localized Surface Plasmons
1.1.3 Excitation of Surface Plasmon Polaritons by Light
1.2 Mie Resonances in Dielectric Nanostructures
1.2.1 Mie Theory
1.2.2 Interactions Between a Sphere and a Dipole
1.2.3 Scattering by a Circular Cylinder
References
Chapter 2: Nanophotonic Devices and Platforms
2.1 Optical Antennas
2.1.1 Properties and Parameters of Optical Antennas
2.1.2 Single Particles as Optical Antennas
2.1.3 Multiparticle Nanoantennas
2.1.4 Controlling Spontaneous Emission with Nanoantennas
2.2 Metamaterials and Metasurfaces
2.2.1 Optically Resonant Building Blocks
2.2.2 Metamaterials
2.2.3 Metasurfaces
References
Chapter 3: Fundamentals of Machine Learning
3.1 Introduction
3.1.1 Brief History of Machine Learning and Deep Learning
3.1.2 Categorization of Machine Learning Techniques
3.1.3 Popular Platforms to Train and Deploy Machine Learning Models
3.2 Deep Neural Networks
3.2.1 Basics of Artificial Neural Networks
3.2.2 Activation Functions
3.2.3 Training of Deep Neural Networks
3.2.4 Overfitting
3.3 Variations of Neural Networks and Popular Models
3.3.1 Variations of Neural Networks
3.3.1.1 Convolutional Neural Networks
3.3.1.2 Recurrent Neural Networks
3.3.2 Popular Deep Learning Models
3.3.2.1 Mixture Density Networks
3.3.2.2 Generative Adversarial Networks
3.3.2.3 Autoencoders
3.4 Miscellaneous Machine Learning Techniques
3.4.1 Dimensionality Reduction
3.4.2 Transfer Learning
3.4.3 Reinforcement Learning
References
Chapter 4: Deep-Learning-Assisted Inverse Design in Nanophotonics
4.1 Inverse Design and Non-uniqueness Problem
4.2 Photonic Multilayer Structures
4.2.1 Planar Multilayer Stacks
4.2.2 Multilayer Core-Shell Nanoparticles
4.3 Metasurfaces
4.4 Photonic Structures with Chiroptical Responses
4.5 Deep-Learning-Assisted Optimization for Inverse Design
References
Chapter 5: Deep-Learning-Enabled Applications in Nanophotonics
5.1 Knowledge Migration by Transfer Learning
5.2 Surrogate Simulators for Inferring Field Quantities
5.3 Interpretation of Optical Information
References
Chapter 6: Nanophotonic and Optical Platforms for Deep Learning
6.1 Deep Learning with Nanophotonic Circuits
6.2 All-Optical Diffractive Deep Neural Networks
6.3 In Situ Training of Photonic Neural Networks
References
Index
