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

Optimization dynamics for partitioned neural networks

D I Tsioutsias1, E Mjolsness

  • 1Yale University, New Haven, CT 06520-8285, USA.

International Journal of Neural Systems
|December 1, 1994
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

Combined in silico/in vivo analysis of mechanisms providing for root apical meristem self-organization and maintenance.

Annals of botany·2012
Same author

Machine learning for science: state of the art and future prospects.

Science (New York, N.Y.)·2001
Same author

Delta-Notch lateral inhibitory patterning in the emergence of ciliated cells in Xenopus: experimental observations and a gene network model.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2000
Same author

Convergence properties of the softassign quadratic assignment algorithm.

Neural computation·1999
Same author

A robust point-matching algorithm for autoradiograph alignment.

Medical image analysis·1999
Same author

A gene network approach to modeling early neurogenesis in Drosophila.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·1998
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

We present a method to model slow communication in partitioned neural networks using objective function transformations. This approach enables efficient parallelization for tasks like image segmentation.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Relaxation-based neural networks are effective for complex computations.
  • Partitioning networks into modules with slow inter-module communication is desirable for modularity and efficiency.
  • Modeling these slow communication channels is crucial for understanding network dynamics.

Purpose of the Study:

  • To investigate relaxation dynamics in partitioned neural networks with slow inter-module communication.
  • To develop a method for modeling slow inter-module communication channels.
  • To demonstrate the functional and efficient parallelization of this algorithm.

Main Methods:

  • Introduced transformations to the original objective function to model slow inter-module communication channels.

Related Experiment Videos

  • Incorporated new state variables for inter-module communication links.
  • Developed a parallel implementation of the relaxation dynamics on a network of workstations.

    • Main Results:

    • Successfully modeled slow inter-module communication channels through objective function transformations.
    • Demonstrated a functional and efficient parallelization of the partitioned neural network algorithm.
    • Achieved effective image segmentation using the parallelized network.

    Conclusions:

    • The proposed method effectively models slow inter-module communication in relaxation-based neural networks.
    • Parallel implementation offers a scalable and efficient approach for complex tasks like image segmentation.
    • The findings have implications for designing and implementing analog hardware for relaxation networks.