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

Training simultaneous recurrent neural network with resilient propagation for static optimization.

Gursel Serpen1, Joel Corra

  • 1Electrical Engineering and Computer Science, The University of Toledo, Toledo, OH 43606, USA. gserpen@eng.utoledo.edu

International Journal of Neural Systems
|October 9, 2002
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

Exploiting mid-range DNA patterns for sequence classification: binary abstraction Markov models.

Nucleic acids research·2012
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 new non-recurrent training algorithm, resilient backpropagation, enhances Simultaneous Recurrent Neural networks. This method achieves superior solutions for optimization problems like the Traveling Salesman Problem with similar computational effort.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Optimization Algorithms

Background:

  • Simultaneous Recurrent Neural networks (SRNNs) are effective for static optimization problems.
  • Training SRNNs typically uses recurrent backpropagation, which can be computationally intensive.
  • Existing methods may not always yield the highest quality solutions for complex optimization tasks.

Purpose of the Study:

  • To introduce a novel non-recurrent training algorithm, resilient backpropagation, for SRNNs.
  • To adapt SRNN weights using resilient backpropagation through an algebraic approach.
  • To evaluate the performance of this neuro-optimizer on static combinatorial optimization problems.

Main Methods:

  • Developed a non-recurrent training algorithm: resilient backpropagation.

Related Experiment Videos

  • Applied an algebraic approach for adapting SRNN weights.
  • Tested the algorithm on the Traveling Salesman Problem (TSP).

    • Main Results:

    • The SRNN trained with resilient backpropagation found superior solutions for the TSP.
    • Performance was evaluated using computational complexity measures.
    • Compared results against standard backpropagation and recurrent backpropagation.

    Conclusions:

    • Resilient backpropagation offers a viable alternative for training SRNNs.
    • The proposed method achieves high-quality solutions for optimization problems like TSP.
    • This approach provides comparable computational effort to existing methods.