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

Multi/infinite dimensional neural networks, multi/infinite dimensional logic theory.

Garimella Rama Murthy1

  • 1International Institute of Information Technology (IIIT), Gachibowli, Hyderabad-500019, AP, India. rammurthy@iiit.net

International Journal of Neural Systems
|July 14, 2005
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

Toward Optimal Synthesis of Discrete-Time Hopfield Neural Network.

IEEE transactions on neural networks and learning systems·2022
Same author

Global dynamics of a class of complex valued neural networks.

International journal of neural systems·2008
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 mathematical model for multi-dimensional neural networks using fully symmetric tensors is presented. This model relates network states to energy function minima, enabling the realization of logic functions and circuits.

Area of Science:

  • * Computational Neuroscience
  • * Mathematical Logic
  • * Tensor Theory

Background:

  • * Neural networks are complex systems with interconnected nodes.
  • * Logic gates perform Boolean operations, forming the basis of computation.
  • * Representing these systems mathematically is crucial for understanding their behavior.

Purpose of the Study:

  • * To develop a mathematical model for multi-dimensional neural networks.
  • * To establish a convergence theorem for these networks.
  • * To explore the relationship between energy functions and logic operations.

Main Methods:

  • * Development of a mathematical model for arbitrary multi-dimensional neural networks.
  • * Representation of network connectivity using fully symmetric tensors.

Related Experiment Videos

  • * Definition of energy functions relating input/output states to tensor structures.

    • Main Results:

    • * A convergence theorem for multi-dimensional neural networks represented by fully symmetric tensors is proven.
    • * Input and output states are linked via an energy function, with minima corresponding to logic gate outputs.
    • * Logic circuits are modeled using block symmetric tensors and associated energy functions.

    Conclusions:

    • * The developed model provides a framework for analyzing multi-dimensional neural networks.
    • * The energy function approach unifies neural network dynamics and logic gate operations.
    • * Infinite dimensional logic theory can be explored using higher-order tensors.