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 Experiment Videos

A cascading structure and training method for multilayer neural networks.

Y Li1, A B Rad

  • 1Department of Electrical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon.

International Journal of Neural Systems
|March 5, 1999
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Adaptive fuzzy approach for a class of uncertain nonlinear systems in strict-feedback form.

ISA transactions·2008
Same author

Identification of nonlinear systems with unknown time delay based on time-delay neural networks.

IEEE transactions on neural networks·2008
Same author

Model-based fault diagnosis in continuous dynamic systems.

ISA transactions·2004
Same author

Development of a circuit for functional electrical stimulation.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2004
Same author

On-line lower-order modeling via neural networks.

ISA transactions·2003
Same author

Self-tuning control of systems with unknown time delay via extended polynomial identification.

ISA transactions·2003
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

A novel cascade training method enhances multilayer neural networks by optimizing subnetworks layer by layer. This efficient approach, validated by linear least squares back-propagation (LSB) and back-propagation (BP), improves neural network performance.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Multilayer neural networks (MNNs) are fundamental in machine learning.
  • Traditional training methods can be computationally intensive and prone to local minima.
  • Developing efficient and effective MNN training strategies is crucial for advancing AI.

Purpose of the Study:

  • To introduce a new structure and cascade training method for multilayer neural networks.
  • To demonstrate an efficient layer-by-layer weight optimization technique.
  • To validate the proposed method's efficacy using established algorithms.

Main Methods:

  • A novel cascade training approach involving sequential subnetwork training.
  • Layer-by-layer optimization of network weights.

Related Experiment Videos

  • Training involves two steps: initial subnetwork training and subsequent subnetwork training using the outputs of the first.
  • Integration of trained subnetworks to form the final MNN.

    • Main Results:

    • The proposed cascade training method successfully creates a trained multilayer neural network.
    • Numerical simulations using linear least squares back-propagation (LSB) and traditional back-propagation (BP) algorithms confirmed the method's efficiency.
    • The layer-by-layer optimization approach proved effective in training subnetworks.

    Conclusions:

    • The presented cascade training method offers an efficient alternative for training multilayer neural networks.
    • The layer-by-layer optimization strategy is a viable technique for improving MNN training.
    • The proposed method shows promise for enhancing the performance and training of neural networks.