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

Classification of Systems-II01:31

Classification of Systems-II

254
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
254
Classification of Systems-I01:26

Classification of Systems-I

357
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
357
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

169
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
169
Aggregates Classification01:29

Aggregates Classification

411
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
411

You might also read

Related Articles

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

Sort by
Same author

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026
Same author

Koopman-Driven Linearized Model-Based Offline Planning With Application to Freeway Ramp Metering.

IEEE transactions on neural networks and learning systems·2025
Same author

Observer based resilient security control for networked nondeterministic Markovian jump systems with cyber attacks and its applications.

Scientific reports·2025
Same author

On Ordered Weighted Averaging Operator and Monotone Takagi-Sugeno-Kang Fuzzy Inference Systems.

IEEE transactions on cybernetics·2025
Same author

Finite-Time Stability Analysis and Stabilization of Switched Affine Systems via an Event-Triggered Strategy.

IEEE transactions on cybernetics·2024
Same author

Security and Safety-Critical Learning-Based Collaborative Control for Multiagent Systems.

IEEE transactions on neural networks and learning systems·2024

Related Experiment Video

Updated: Oct 10, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

955

Evolving Deep Architecture Generation with Residual Connections for Image Classification Using Particle Swarm

Tom Lawrence1, Li Zhang2, Kay Rogage1

  • 1Department of Computer and Information Sciences, Faculty of Engineering and Environment, Northumbria University, Newcastle upon Tyne NE1 8ST, UK.

Sensors (Basel, Switzerland)
|December 10, 2021
PubMed
Summary

This study introduces a new particle swarm optimization (PSO) algorithm for automated deep neural architecture generation. The method effectively designs deep networks with residual connections, outperforming existing approaches and improving accuracy.

Keywords:
deep architecture generationdeep residual networkimage classificationparticle swarm optimization

More Related Videos

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

677
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.3K

Related Experiment Videos

Last Updated: Oct 10, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

955
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

677
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.3K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Deep Learning

Background:

  • Automated deep neural architecture generation is a growing research area.
  • Existing methods have limitations in optimizing design choices or search space for residual/dense networks.

Purpose of the Study:

  • To propose a novel particle swarm optimization (PSO)-based algorithm for automated deep architecture generation.
  • To devise deep networks with residual connections while optimizing key design choices through a comprehensive search.

Main Methods:

  • A variant of particle swarm optimization (PSO) with a new encoding scheme and search mechanism.
  • The search mechanism utilizes non-uniformly randomly selected neighboring and global promising solutions.
  • The encoding scheme describes convolutional neural network architectures incorporating residual connections.

Main Results:

  • The proposed model outperforms current state-of-the-art methods in architecture generation on benchmark datasets.
  • The algorithm generates diverse residual architectures by leveraging diverse neighboring and global solutions.
  • Devised networks demonstrate improved capability in addressing vanishing gradient problems.

Conclusions:

  • The novel PSO-based algorithm effectively generates optimal deep neural architectures with residual connections.
  • The method enhances performance and diversity compared to existing automated architecture generation techniques.
  • The approach offers a significant improvement in mean accuracy (up to 4.34%) by tackling vanishing gradients.