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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

163
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
163
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

241
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
241
Ampere-Maxwell's Law: Problem-Solving01:17

Ampere-Maxwell's Law: Problem-Solving

887
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...
887
Maxwell-Boltzmann Distribution: Problem Solving01:20

Maxwell-Boltzmann Distribution: Problem Solving

2.0K
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
2.0K

You might also read

Related Articles

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

Sort by
Same author

A Large-Scale Peripheral Blood Cell Dataset for Automated Hematological Analysis.

Scientific data·2026
Same author

MOLiNAS: multi-objective lightweight neural architecture search for whole-slide multi-class blood cell segmentation.

Health information science and systems·2025
Same author

Multi-teacher based knowledge distillation for retinal vessel segmentation.

Health information science and systems·2025
Same author

Neural Architecture Search for biomedical image classification: A comparative study across data modalities.

Artificial intelligence in medicine·2025
Same author

MedSegBench: A comprehensive benchmark for medical image segmentation in diverse data modalities.

Scientific data·2024
Same author

Evolutionary Architecture Optimization for Retinal Vessel Segmentation.

IEEE journal of biomedical and health informatics·2023
Same journal

DARUMA: a gateway to fast and easy prediction of intrinsically disordered regions.

PeerJ. Computer science·2026
Same journal

Alzheimer's disease detection using a quantum deep neural network with Haralick feature extraction and simulated annealing optimization.

PeerJ. Computer science·2026
Same journal

Network anomaly detection using Deep Autoencoder and parallel Artificial Bee Colony algorithm-trained neural network.

PeerJ. Computer science·2026
Same journal

An anomaly detection model for multivariate time series with anomaly perception.

PeerJ. Computer science·2026
Same journal

Retraction: A wormhole attack detection method for tactical wireless sensor networks.

PeerJ. Computer science·2026
Same journal

Evaluation of mental disorder with prioritization of its type by utilizing the bipolar complex fuzzy decision-making approach based on Schweizer-Sklar prioritized aggregation operators.

PeerJ. Computer science·2026
See all related articles

Related Experiment Video

Updated: Nov 10, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

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

Published on: August 16, 2024

642

Multi-objective simulated annealing for hyper-parameter optimization in convolutional neural networks.

Ayla Gülcü1, Zeki Kuş1

  • 1Computer Science, Fatih Sultan Mehmet University, Istanbul, Turkey.

Peerj. Computer Science
|April 5, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a Multi-Objective Simulated Annealing (MOSA) algorithm to optimize Convolutional Neural Network (CNN) hyperparameters, balancing classification accuracy and computational complexity. MOSA outperforms traditional methods, generating effective CNN architectures with reduced complexity.

Keywords:
Convolutional neural networksHyper-parameter optimizationMulti-objectiveSimulated annealing

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

9.6K
Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
10:36

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption

Published on: November 3, 2023

1.8K

Related Experiment Videos

Last Updated: Nov 10, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

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

Published on: August 16, 2024

642
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.6K
Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
10:36

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption

Published on: November 3, 2023

1.8K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Optimization Algorithms

Background:

  • Convolutional Neural Networks (CNNs) are powerful tools for image classification but require extensive hyperparameter tuning.
  • Optimizing CNNs involves a trade-off between classification accuracy and computational complexity.
  • Existing methods often focus on a single objective, potentially compromising the other.

Purpose of the Study:

  • To model CNN hyperparameter optimization as a bi-criteria problem, considering both classification accuracy and computational complexity.
  • To develop and evaluate a Multi-Objective Simulated Annealing (MOSA) algorithm for this bi-criteria optimization.
  • To compare MOSA's performance against single-objective optimization methods and state-of-the-art architectures.

Main Methods:

  • Formulated CNN hyperparameter optimization as a bi-criteria problem (accuracy vs. floating-point operations).
  • Developed a Multi-Objective Simulated Annealing (MOSA) algorithm to find optimal trade-offs.
  • Utilized the CIFAR-10 dataset for benchmarking.
  • Compared MOSA with single-objective Simulated Annealing (SA) using front evaluation metrics (generational distance, spacing, spread).
  • Evaluated selected MOSA-generated configurations against state-of-the-art architectures.

Main Results:

  • MOSA demonstrated more effective search of the objective space compared to single-objective SA.
  • MOSA-generated CNN configurations were not dominated by existing state-of-the-art architectures.
  • MOSA configurations showed superior performance in multi-objective settings.
  • The algorithm effectively balances computational complexity with test accuracy.

Conclusions:

  • The proposed MOSA algorithm is a valuable tool for CNN hyperparameter optimization, particularly when computational resources are constrained.
  • MOSA provides high-quality solutions that effectively balance classification accuracy and computational complexity.
  • This approach offers a competitive alternative to traditional single-objective optimization and manual architecture design.