Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Measurement of X-ray Beam Coherence along Multiple Directions Using 2-D Checkerboard Phase Grating10:39

Measurement of X-ray Beam Coherence along Multiple Directions Using 2-D Checkerboard Phase Grating

10.1K
The measurement protocol and data analysis procedure are given for obtaining transverse coherence of a synchrotron radiation X-ray source along four directions simultaneously using a single 2-D checkerboard phase grating. This simple technique can be applied for complete transverse coherence characterization of X-ray sources and X-ray...
10.1K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

3.3K
An object segmentation protocol for orbital computed tomography (CT) images is introduced. The methods of labeling the ground truth of orbital structures by using super-resolution, extracting the volume of interest from CT images, and modeling multi-label segmentation using 2D sequential U-Net for orbital CT images are explained for supervised...
3.3K
Positive Reinforcement Studies07:06

Positive Reinforcement Studies

24.8K
Researchers study learning of a behavior through the use of operant conditioning. This type of learning involves associating the behavior with a consequence, which is a reward or punishment. If the consequence is a reward, it leads to reinforcement of the desired behavior. One type of reinforcement approach is positive reinforcement, where the behavior is rewarded with an artificial, natural, or social reinforcer. Studies using positive reinforcement as a tool can help tease out important...
24.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

10.6K
This is a method for training a multi-slice U-Net for multi-class segmentation of cryo-electron tomograms using a portion of one tomogram as a training input. We describe how to infer this network to other tomograms and how to extract segmentations for further analyses, such as subtomogram averaging and filament...
10.6K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

9.8K
The purpose of this protocol is to utilize pre-built convolutional neural nets to automate behavior tracking and perform detailed behavior analysis. Behavior tracking can be applied to any video data or sequences of images and is generalizable to track any user-defined...
9.8K
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

4.4K
This tutorial describes a simple method to construct a deep learning algorithm for performing 2-class sequence classification of metagenomic...
4.4K

You might also read

Related Articles

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

Sort by
Same author

Improved temporal characteristics for post-compressed pulses via application-tailored nonlinear polarization ellipse rotation.

Optics letters·2024
Same author

Temporal pulse quality of a Yb:YAG burst-mode laser post-compressed in a multi-pass cell.

Optics letters·2021
Same author

Phase-locked and mode-locked multicore photonic crystal fiber laser with a saturable absorber.

Optics express·2021
Same author

Kerr-lens mode-locked Yb:LuAG ceramic thin-disk laser.

Optics letters·2021
Same author

Sarcopenia as a Predictor of Survival Among Patients With Organ Metastatic Cervical Cancer.

Nutrition in clinical practice : official publication of the American Society for Parenteral and Enteral Nutrition·2020
Same author

Prognostic value of neutrophil-to-lymphocyte ratio in early-stage ovarian clear-cell carcinoma.

Journal of gynecologic oncology·2019

Related Experiment Video

Updated: Jan 19, 2026

Measurement of X-ray Beam Coherence along Multiple Directions Using 2-D Checkerboard Phase Grating
10:39

Measurement of X-ray Beam Coherence along Multiple Directions Using 2-D Checkerboard Phase Grating

Published on: October 11, 2016

10.1K

Deep reinforcement learning for coherent beam combining applications.

Henrik Tünnermann, Akira Shirakawa

    Optics Express
    |September 13, 2019
    PubMed
    Summary

    Reinforcement learning and neural networks achieved laser phase stabilization comparable to PID controllers. This AI approach also shows potential for predicting relative phase noise in laser systems.

    Area of Science:

    • Laser physics and optical engineering.
    • Artificial intelligence and machine learning applications.

    Background:

    • Scaling laser power requires combining multiple laser emitters.
    • Coherent beam combining necessitates precise relative optical phase stabilization.
    • Traditional methods like PID controllers are effective but may have limitations.

    Purpose of the Study:

    • To investigate the application of reinforcement learning (RL) and neural networks (NN) for coherent beam combining.
    • To compare the performance of NN-based phase stabilization against traditional PID controllers.
    • To explore the potential of NNs in predicting relative phase noise.

    Main Methods:

    • Utilizing a neural network initialized randomly.
    • Training the NN using reinforcement learning to develop a phase stabilization policy.

    More Related Videos

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.3K
    Positive Reinforcement-Operant Conditioning Studies
    07:06

    Positive Reinforcement-Operant Conditioning Studies

    Published on: April 30, 2023

    24.8K

    Related Experiment Videos

    Last Updated: Jan 19, 2026

    Measurement of X-ray Beam Coherence along Multiple Directions Using 2-D Checkerboard Phase Grating
    10:39

    Measurement of X-ray Beam Coherence along Multiple Directions Using 2-D Checkerboard Phase Grating

    Published on: October 11, 2016

    10.1K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.3K
    Positive Reinforcement-Operant Conditioning Studies
    07:06

    Positive Reinforcement-Operant Conditioning Studies

    Published on: April 30, 2023

    24.8K
  • Implementing a software-based proportional-integral-derivative (PID) controller for comparison.
  • Evaluating the NN's capability to predict relative phase noise.

    • Main Results:

    • The RL-trained NN successfully converged to a phase stabilization policy.
    • The NN's performance in phase stabilization was comparable to a software PID controller.
    • The study demonstrated the NN's ability to predict relative phase noise.

    Conclusions:

    • Reinforcement learning and neural networks offer a viable alternative for laser phase stabilization in coherent beam combining.
    • NNs present a potential advantage in predicting relative phase noise, aiding system optimization.
    • This AI-driven approach shows promise for advancing high-power laser system development.