Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Nov 13, 2025

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

Published on: September 5, 2019

Tackling Photonic Inverse Design with Machine Learning.

Zhaocheng Liu¹, Dayu Zhu¹, Lakshmi Raju¹

¹School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA 30332 USA.

Advanced Science (Weinheim, Baden-Wurttemberg, Germany)

|March 15, 2021

Summary

This summary is machine-generated.

Related Concept Videos

Ampere-Maxwell's Law: Problem-Solving

Ampere-Maxwell's Law: Problem-Solving

A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...

Maxwell-Boltzmann Distribution: Problem Solving

Maxwell-Boltzmann Distribution: Problem Solving

Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by

Ampere's Law: Problem-Solving

Ampere's Law: Problem-Solving

Ampere's law states that for any closed looped path, the line integral of the magnetic field along the path equals the vacuum permeability times the current enclosed in the loop. If the fingers of the right hand curl along the direction of the integration path, the current in the direction of the thumb is considered positive. The current opposite to the thumb direction is considered negative.
Specific steps need to be considered while calculating the symmetric magnetic field distribution...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Monitoring visibility gaps in global river water-quality archives: a basin-scale framework for environmental management prioritization.

Journal of environmental management·2026

Same author

Water-level operation creates redox windows that govern greenhouse-gas pathways in reservoir drawdown soils.

Journal of environmental management·2026

Same author

Global burden of breast cancer and its association with red meat consumption: spatiotemporal trends, projections, and triangulation of evidence.

World journal of surgical oncology·2026

Same author

Detection of Ultralow-Frequency ctDNA Mutations Using a Dual Hairpin-Competition CRISPR/Cas14a System.

Analytical chemistry·2026

Same author

An isaindigotone-based NIR fluorogenic probe for visualizing mitochondrial DNA G-quadruplexes in living cells.

Chemical communications (Cambridge, England)·2026

Same author

MxDiffusion: A Physics-Aware Maxwell's Law-Guided Diffusion Model Strategy for Inverse Photonic Metasurface Design.

Nano letters·2026

Machine learning (ML) accelerates scientific discovery by automating predictions from data. This review highlights ML, especially deep learning, for advancing photonic inverse design strategies.

Area of Science:

Artificial Intelligence
Photonics and Optics

Background:

Machine learning (ML) automates prediction and decision-making from complex data, becoming a key AI tool.
Data-driven approaches are increasingly integrated into scientific research, driving progress across fields like quantum physics, chemistry, and medical imaging.
ML is emerging as a powerful tool in photonics and optics for tackling the inverse design problem.

Purpose of the Study:

To summarize recent advancements in machine learning-enabled photonic design strategies.
To focus on deep learning methods for addressing complex, high-dimensional structure design challenges in photonics.

Main Methods:

Review of recent literature on machine learning applications in photonic design.
Focus on deep learning algorithms for inverse design problems.

Keywords:

inverse design machine learning nanophotonics neural networks

More Related Videos

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Published on: April 4, 2017

Lensless Fluorescent Microscopy on a Chip

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

Related Experiment Videos

Last Updated: Nov 13, 2025

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

Published on: September 5, 2019

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Published on: April 4, 2017

Lensless Fluorescent Microscopy on a Chip

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

Analysis of strategies for high degrees-of-freedom structure design.

Main Results:

Machine learning, particularly deep learning, shows rapid progress in photonic inverse design.
These methods offer effective solutions for complex photonic structure optimization.
The integration of ML is transforming photonic research and development.

Conclusions:

Machine learning is an indispensable tool revolutionizing photonic design.
Deep learning methods are crucial for solving intricate photonic inverse design challenges.
The field is rapidly advancing, offering new possibilities for optical device innovation.