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

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

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

Sort by

Same author

Severe trauma care: advances and future directions in diagnostic and therapeutic techniques and information technology support.

Medical review (2021)·2026

Same author

Suppressor tRNA-mediated conditionally replicating live vaccine effectively protects pigs against Seneca Valley virus challenge.

NPJ vaccines·2026

Same author

Phase measurement and compensation method for a waveguide beam based on an on-chip 90° optical hybrid mixer.

Optics express·2026

Same author

ATP Synthase Subunit b Binds Cry2Ab and Mediates Its Toxicity in <i>Grapholita molesta</i>.

Journal of agricultural and food chemistry·2026

Same author

Balanced Sacrospinous Ligament Fixation in Uterine Prolapse: A Preliminary Retrospective Comparative Study.

International urogynecology journal·2026

Same author

Ontogenetic and spatial variation in the feeding habits of Tripneustes gratilla.

Marine environmental research·2026

Search research articles

Related Experiment Video

Updated: Jul 15, 2025

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Published on: September 25, 2020

End-to-End Diverse Metasurface Design and Evaluation Using an Invertible Neural Network.

Yunxiang Wang¹, Ziyuan Yang², Pan Hu¹

¹Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA.

Nanomaterials (Basel, Switzerland)

|September 28, 2023

Summary

This study introduces an invertible neural network (INN) for efficient metasurface design, overcoming challenges in inverse design by simultaneously modeling forward and inverse processes for novel optical applications.

Keywords:

deep learning holograms invertible neural network metalens metasurface

More Related Videos

Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces

Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces

Published on: June 7, 2019

Fabrication of Magnetic Platforms for Micron-Scale Organization of Interconnected Neurons

Fabrication of Magnetic Platforms for Micron-Scale Organization of Interconnected Neurons

Published on: July 14, 2021

Related Experiment Videos

Last Updated: Jul 15, 2025

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Published on: September 25, 2020

Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces

Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces

Published on: June 7, 2019

Fabrication of Magnetic Platforms for Micron-Scale Organization of Interconnected Neurons

Fabrication of Magnetic Platforms for Micron-Scale Organization of Interconnected Neurons

Published on: July 14, 2021

Area of Science:

Optics and Photonics
Artificial Intelligence
Materials Science

Background:

Deep learning models offer accuracy and efficiency for metasurface design.
Traditional frameworks use separate models for forward (response prediction) and backward (design generation) paths.
The one-to-many mapping in inverse design is a significant challenge for deep learning models.

Purpose of the Study:

To develop an efficient and automated end-to-end metasurface design framework.
To address the challenge of one-to-many mapping in inverse design.
To improve the efficiency and effectiveness of deep learning-based metasurface design.

Main Methods:

Utilized an invertible neural network (INN) to simultaneously model forward and inverse processes.
Integrated the INN with the angular spectrum method for automated design and evaluation.
Trained the INN to implicitly capture a probabilistic model for the inverse process, recovering the complete posterior over the parameter space.

Main Results:

Developed an efficient, automated, end-to-end metasurface design and evaluation framework.
Enabled the generation of novel metasurface designs not present in training data.
Successfully designed high-efficiency metalenses and dual-polarization metasurface holograms.

Conclusions:

The INN approach provides a general method for optical inverse design problems.
This framework significantly speeds up the metasurface design process, eliminating human intervention.
The method extends beyond dielectric metasurface design to diverse optical fields.