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

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

1.0K
The present protocol describes a novel end-to-end salient object detection algorithm. It leverages deep neural networks to enhance the precision of salient object detection within intricate environmental...
1.0K
Deep Neural Networks for Image-Based Dietary Assessment13:19

Deep Neural Networks for Image-Based Dietary Assessment

9.9K
The goal of the work presented in this article is to develop technology for automated recognition of food and beverage items from images taken by mobile devices. The technology comprises of two different approaches - the first one performs food image recognition while the second one performs food image...
9.9K
Preparation of Binary and Ternary Deep Eutectic Systems06:15

Preparation of Binary and Ternary Deep Eutectic Systems

12.7K
This protocol aims to standardize the preparation of deep eutectic systems throughout the scientific community so that these systems can be...
12.7K
Analyzing the Size, Shape, and Directionality of Networks of Coupled Astrocytes10:10

Analyzing the Size, Shape, and Directionality of Networks of Coupled Astrocytes

9.3K
Here we present a protocol to assess the organization of astrocytic networks. The described method minimizes bias to provide descriptive measures of these networks such as cell count, size, area, and position within a nucleus. Anisotropy is assessed with a vectorial...
9.3K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

829
This article describes a set of methods for measuring the suppressive ability of sniffing alcoholic beverages on the wasabi-elicited stinging...
829
Visualization of Neural and Vascular Networks in a Chicken Embryo03:33

Visualization of Neural and Vascular Networks in a Chicken Embryo

471
Source: Delalande, J., et.al. Dual Labeling of Neural Crest Cells and Blood Vessels Within Chicken Embryos Using ChickGFP Neural Tube Grafting and Carbocyanine Dye DiI Injection. J. Vis. Exp. (2015)This video demonstrates the transplantation of a GFP-labeled donor neural tube from a stage-matched transgenic chicken embryo into a recipient embryo at the level of somites one to seven, followed by vascular labeling using a lipophilic fluorescent dye. The combined approach allows for direct...
471

You might also read

Related Articles

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

Sort by
Same author

On-chip wave chaos for photonic extreme learning.

Optics letters·2025
Same author

Interdisciplinary Projects in Biology and Chemistry.

Chimia·2025
Same author

Training of physical neural networks.

Nature·2025
Same author

Machine-learning model generates images using light.

Nature·2025
Same author

Principles and metrics of extreme learning machines using a highly nonlinear fiber.

Nanophotonics (Berlin, Germany)·2025
Same author

Guided nonlinear optics for information processing.

Nanophotonics (Berlin, Germany)·2025
Same journal

Erratum: Bacterial Turbulence at Compressible Fluid Interfaces [Phys. Rev. Lett. 136, 138301 (2026)].

Physical review letters·2026
Same journal

Unveiling Light-Quark Yukawa Flavor Structure via Dihadron Fragmentation at Lepton Colliders.

Physical review letters·2026
Same journal

Adaptable Route to Fast Coherent State Transport via Bang-Bang-Bang Protocols.

Physical review letters·2026
Same journal

Topological Transition and Emergence of Elasticity of Dislocation in Skyrmion Lattice: Beyond Kittel's Magnetic-Polar Analogy.

Physical review letters·2026
Same journal

Pound-Drever-Hall Method for Superconducting-Qubit Readout.

Physical review letters·2026
Same journal

Coupling a ^{73}Ge Nuclear Spin to an Electrostatically Defined Quantum Dot in Silicon.

Physical review letters·2026
See all related articles

Related Experiment Video

Updated: Jan 20, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Coupled Nonlinear Delay Systems as Deep Convolutional Neural Networks.

Bogdan Penkovsky1, Xavier Porte1, Maxime Jacquot1

  • 1FEMTO-ST/Optics Dept., UMR CNRS 6174, Université Bourgogne Franche-Comté, 15B avenue des Montboucons, 25030 Besançon Cedex, France.

Physical Review Letters
|September 7, 2019
PubMed
Summary
This summary is machine-generated.

Deep neural networks, inspired by reservoir computing, offer efficient emulation on diverse hardware. This novel approach avoids inefficient computations, significantly improving time series prediction accuracy.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Preparation of Binary and Ternary Deep Eutectic Systems
06:15

Preparation of Binary and Ternary Deep Eutectic Systems

Published on: October 31, 2019

12.7K

Related Experiment Videos

Last Updated: Jan 20, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Preparation of Binary and Ternary Deep Eutectic Systems
06:15

Preparation of Binary and Ternary Deep Eutectic Systems

Published on: October 31, 2019

12.7K

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Dynamical Systems

Background:

  • Neural network emulation on current hardware is inefficient.
  • Reservoir computing offers substrate implementation insights but lags deep learning.
  • Time-delay reservoirs provide a foundation for deep network extension.

Purpose of the Study:

  • To extend time-delay reservoirs to deep networks.
  • To demonstrate conceptual correspondence between these deep networks and deep convolutional neural networks.
  • To improve the efficiency and accuracy of neural network emulation.

Main Methods:

  • Extending time-delay reservoirs to create deep networks.
  • Leveraging substrate-level convolution via drive-response properties of dynamical systems.
  • Avoiding computationally expensive vector-matrix products between layers.

Main Results:

  • Deep time-delay reservoirs conceptually match deep convolutional neural networks.
  • Convolution is intrinsically realized at the substrate level.
  • Significant accuracy improvements (order of magnitude) in Mackey-Glass and Lorenz time series prediction compared to singleton reservoirs.

Conclusions:

  • Deep time-delay reservoirs offer a novel, efficient alternative to traditional deep learning architectures.
  • This approach overcomes the efficiency bottleneck in neural network emulation on current computing substrates.
  • The findings pave the way for more powerful and efficient AI implementations.