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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

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...
Lagrange Multipliers: Two Constraints01:28

Lagrange Multipliers: Two Constraints

The method of Lagrange multipliers with two constraints is used to optimize a function subject to two independent constraints. In many applications, the objective function represents a quantity to be maximized or minimized, such as cost, area, distance, or energy. The two constraints represent requirements that the solution must satisfy, such as fixed volume, limited resources, or prescribed dimensions.For a function of three variables, each constraint forms a surface in three-dimensional space.
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

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...

You might also read

Related Articles

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

Sort by
Same author

Enhancing X-ray Image Classification through Heterogeneous Federated Learning with Natural Image-Augmented Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Developing and Testing a Brief Mindfulness Just-in-Time Adaptive Intervention to Reduce Stress Among Caregivers of People With Dementia: Quasi-Experimental Study.

JMIR aging·2026
Same author

Enhancing Generalization and Scalability for Multi-Objective Optimization with Population Pre-Training.

Evolutionary computation·2026
Same author

scBIT: Integrating Single-cell Transcriptomic Data into fMRI-based Prediction for Alzheimer's Disease Diagnosis.

IEEE transactions on medical imaging·2026
Same author

Spatiotemporal Decoupled Learning for Spiking Neural Networks.

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

Explainable Molecular Property Prediction: Aligning Chemical Concepts With Predictions via Language Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Related Experiment Video

Updated: Jul 1, 2026

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
11:53

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Published on: December 9, 2012

Hybrid multiobjective evolutionary design for artificial neural networks.

Chi-Keong Goh1, Eu-Jin Teoh, Kay Chen Tan

  • 1Data Storage Institute, Agency for Science, Technology, and Research, Singapore. Goh_Chi_Keong@dsi.astar.edu.sg

IEEE Transactions on Neural Networks
|September 10, 2008
PubMed
Summary
This summary is machine-generated.

This study introduces a novel hybrid evolutionary approach to optimize artificial neural networks (ANNs). The method uses a geometrical measure for efficient neuron selection, improving training speed and performance.

Related Experiment Videos

Last Updated: Jul 1, 2026

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
11:53

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Published on: December 9, 2012

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Evolutionary algorithms mimic biological evolution for stochastic search.
  • Artificial neural networks (ANNs) increasingly use evolutionary approaches for training.
  • Optimizing ANN performance and architecture simultaneously often leads to slow training.

Purpose of the Study:

  • To develop a geometrical measure using singular value decomposition (SVD) to estimate the optimal number of neurons for single-hidden-layer feedforward neural networks (SLFNs).
  • To introduce a hybrid multiobjective evolutionary approach for efficient ANN training and architectural adaptation.
  • To enhance the training process by incorporating variable-length representations, architectural recombination, and a microhybrid genetic algorithm (microHGA).

Main Methods:

  • A geometrical measure based on SVD for estimating neuron requirements in SLFNs.
  • A hybrid multiobjective evolutionary algorithm featuring variable-length representations for flexible network structures.
  • An architectural recombination procedure guided by the geometrical measure for adaptive neuron adjustment and information exchange.
  • A microhybrid genetic algorithm (microHGA) with adaptive local search for fine-tuning network parameters.

Main Results:

  • The proposed geometrical measure effectively estimates the necessary number of neurons for SLFNs.
  • The hybrid evolutionary approach demonstrates efficient adaptation of neural network architectures.
  • The microHGA with adaptive local search provides effective local fine-tuning, improving overall performance.
  • Validation across diverse datasets confirms the effectiveness and contributions of the proposed approach compared to existing algorithms.

Conclusions:

  • The developed geometrical measure and hybrid evolutionary approach offer a significant advancement in training artificial neural networks.
  • This method addresses the challenge of slow training times associated with simultaneous optimization of ANN performance and architecture.
  • The approach provides a robust and adaptable framework for designing and training efficient neural networks.