Deep learning for nano-photonic materials -- The solution to everything!?
arXiv:2310.08618 · doi:10.1016/j.cossms.2023.101129
Abstract
Deep learning is currently being hyped as an almost magical tool for solving all kinds of difficult problems that computers have not been able to solve in the past. Particularly in the fields of computer vision and natural language processing, spectacular results have been achieved. The hype has now infiltrated several scientific communities. In (nano-)photonics, researchers are trying to apply deep learning to all kinds of forward and inverse problems. A particularly challenging problem is for instance the rational design of nanophotonic materials and devices. In this opinion article, I will first discuss the public expectations of deep learning and give an overview of the quite different scales at which actors from industry and research are operating their deep learning models. I then examine the weaknesses and dangers associated with deep learning. Finally, I'll discuss the key strengths that make this new set of statistical methods so attractive, and review a personal selection of opportunities that shouldn't be missed in the current developments.
arXiv comment13 pages, 7 figures
References in corpus (47)
- Explaining and Harnessing Adversarial Examples
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- An Introduction to Variational Autoencoders
- PaLM: Scaling Language Modeling with Pathways
- A Survey of Deep Learning Techniques for Autonomous Driving
- One pixel attack for fooling deep neural networks
- Sparks of Artificial General Intelligence: Early experiments with GPT-4
- Deep learning for universal linear embeddings of nonlinear dynamics
- Training deep neural networks for the inverse design of nanophotonic structures
- Fourier Neural Operator for Parametric Partial Differential Equations
- A Generative Model for Inverse Design of Metamaterials
- PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
- Deep neural networks for the evaluation and design of photonic devices
- Using Deep Learning and Google Street View to Estimate the Demographic Makeup of the US
- A Survey on Metric Learning for Feature Vectors and Structured Data
- Discovering physical concepts with neural networks
- Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
- Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
- No Language Left Behind: Scaling Human-Centered Machine Translation
- The Unreasonable Effectiveness of Deep Learning in Artificial Intelligence
- Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
- Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward
- Deep learning enhanced mobile-phone microscopy
- Physics-Informed Neural Operator for Learning Partial Differential Equations
- The Curse of Recursion: Training on Generated Data Makes Models Forget
- Mapping the global design space of nanophotonic components using machine learning pattern recognition
- Pushing the limits of optical information storage using deep learning
- Elucidating the Behavior of Nanophotonic Structures Through Explainable Machine Learning Algorithms
- Knowledge Discovery In Nanophotonics Using Geometric Deep Learning
- Galaxy Merger Rates up to z 3 using a Bayesian Deep Learning Model A Major-Merger classifier using IllustrisTNG Simulation data
- Deep learning enabled design of complex transmission matrices for universal optical components
- Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse Design
- A newcomer's guide to deep learning for inverse design in nano-photonics
- MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
- A neural operator-based surrogate solver for free-form electromagnetic inverse design
- Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
- Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
- Deep neural networks for the prediction of the optical properties and the free-form inverse design of metamaterials
- Deep learning enabled strategies for modelling of complex aperiodic plasmonic metasurfaces of arbitrary size
- The Effects of Regularization and Data Augmentation are Class Dependent
- All-Optical tunability of metalenses infiltrated with liquid crystals
- Physics-Based Deep Neural Networks for Beam Dynamics in Charged Particle Accelerators
- Learning in High Dimension Always Amounts to Extrapolation
- Inverse Design of All-dielectric Metasurfaces with Bound States in the Continuum
- Inverse design with flexible design targets via deep learning: Tailoring of electric and magnetic multipole scattering from nano-spheres
- Monitoring MBE substrate deoxidation via RHEED image-sequence analysis by deep learning
- Physics-data-driven intelligent optimization for large-scale meta-devices