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 biologically-inspired improved MAXNET.

O Yadid-Pecht1, M Gur

  • 1Dept. of Biomed. Eng., Technion-Israel Inst. of Technol., Haifa.

IEEE Transactions on Neural Networks
|January 1, 1995
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

Clinical characteristics and short-term outcomes of adult patients with urolithiasis: first report from Somalia.

European review for medical and pharmacological sciences·2023
Same author

Our kidneys and teeth may be closer than we think: relationship between dental calculi and renal stone burden grading in a patient series from Somalia.

European review for medical and pharmacological sciences·2023
Same author

The Q359K/T360K mutation causes cystic fibrosis in Georgian Jews.

Journal of cystic fibrosis : official journal of the European Cystic Fibrosis Society·2018
Same author

Epicardial fat thickness is associated with severity of disease in patients with chronic obstructive pulmonary disease.

European review for medical and pharmacological sciences·2016
Same author

The predictive effect of initial complete blood count of intensive care unit patients on mortality, length of hospitalization, and nosocomial infections.

European review for medical and pharmacological sciences·2016
Same author

Coronary collateral circulation in patients with chronic coronary total occlusion; its relationship with cardiac risk markers and SYNTAX score.

Perfusion·2014
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

This study introduces a modified MAXNET with dynamic weights, significantly improving convergence speed. A hardware implementation of this biologically-inspired neural network is also presented.

Area of Science:

  • Computational Neuroscience
  • Artificial Neural Networks
  • Biologically-Inspired Computing

Background:

  • The original MAXNET architecture features constant weights, limiting its adaptability and convergence efficiency.
  • Dynamic weight adjustment is crucial for enhancing the performance of neural network models.

Purpose of the Study:

  • To propose a biologically-inspired modification to the MAXNET architecture.
  • To investigate the impact of dynamic weight changes on network performance.
  • To present a hardware implementation of the modified network.

Main Methods:

  • Modification of the MAXNET algorithm to incorporate dynamically changing weights.
  • Comparative analysis of convergence rates between the original and modified MAXNET.

Related Experiment Videos

  • Design and presentation of a simple hardware implementation for the enhanced network.

    • Main Results:

    • The modified MAXNET demonstrates a drastic improvement in convergence rate compared to the original.
    • Dynamic weight adjustment leads to significantly faster learning and adaptation.
    • A feasible hardware implementation of the biologically-inspired modification is achieved.

    Conclusions:

    • The proposed biologically-inspired modification significantly enhances MAXNET's convergence rate.
    • Dynamic weights are key to improving neural network efficiency.
    • The developed hardware implementation offers a practical approach for real-world applications.