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

Learning attractors in an asynchronous, stochastic electronic neural network

P Del Giudice1, S Fusi, D Badoni

  • 1Istituto Superiore di Sanità, Physics Laboratory, Rome, Italy.

Network (Bristol, England)
|December 23, 1998
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

Evaluation of the usefulness of routine molecular biology for the diagnosis of primary syphilis by assessing the serological status of patients with PCR-confirmed syphilitic ulcers.

Journal of the European Academy of Dermatology and Venereology : JEADV·2023
Same author

First case of Sweet's syndrome after tattooing.

Annales de dermatologie et de venereologie·2022
Same author

Increased incidence of cutaneous Staphylococcusaureus infections after the 2010 floods in the Var department of France: Rumour or reality?

Annales de dermatologie et de venereologie·2022
Same author

Disseminated febrile punctiform erythematous and petechial eruption in children - a paraviral phenomenon.

Journal of the European Academy of Dermatology and Venereology : JEADV·2022
Same author

Impact of containment and social distancing on the number of community-acquired Staphylococcus aureus skin infections.

Journal of the European Academy of Dermatology and Venereology : JEADV·2022
Same author

First case of documented Lyme borreliosis in the Alpes-Maritimes department of South-Eastern France: Erythema chronicum migrans associated with Borrelia afzelii.

Annales de dermatologie et de venereologie·2022
Same journal

Enhancing IoT security: A Creative Swagger Optimization algorithm for DDoS defence.

Network (Bristol, England)·2026
Same journal

Parametric optimization for electrical discharge diamond grinding (EDDG) system using dual approach.

Network (Bristol, England)·2025
Same journal

A novel lung cancer diagnosis model using hybrid convolution (2D/3D)-based adaptive DenseUnet with attention mechanism.

Network (Bristol, England)·2025
Same journal

Hybrid optimization enabled Eff-FDMNet for Parkinson's disease detection and classification in federated learning.

Network (Bristol, England)·2025
Same journal

AI-driven plant disease detection with tailored convolutional neural network.

Network (Bristol, England)·2025
Same journal

Layer modified residual Unet++ for speech enhancement using Aquila Black widow optimizer algorithm.

Network (Bristol, England)·2025
See all related articles

The LANN27 electronic device uses stochastic Hebbian learning to create dynamic attractors that record stimulus statistics and extract prototypes from noisy data. This neural network system adapts over time, functioning as a palimpsest to incorporate new information.

Area of Science:

  • Neuroscience
  • Electronic Engineering
  • Computational Intelligence

Background:

  • Artificial neural networks (ANNs) are crucial for modeling brain functions.
  • Plastic synapses and dynamic neurons are key components in biologically inspired computing.
  • Understanding collective dynamics in complex systems is essential for advancing AI.

Purpose of the Study:

  • To investigate the collective dynamics of the LANN27 electronic device.
  • To analyze the learning process and attractor formation in a fully connected neural network.
  • To propose methods for studying complex neural system dynamics and outcomes.

Main Methods:

  • Implementation of a 27-neuron, 351-synapse electronic network with stochastic Hebbian learning.
  • Modeling of dynamic neurons (fast) and plastic synapses (slow) with analogue learning.

Related Experiment Videos

  • Analysis of network dynamics, attractor states, and prototype extraction capabilities.

    • Main Results:

    • The LANN27 network forms attractors reflecting large-scale stimulus statistics.
    • The network exhibits palimpsest-like behavior, adapting to changing stimulus environments.
    • Attractors serve as prototypes, successfully retrieving noisy versions of training stimuli.

    Conclusions:

    • The LANN27 device demonstrates a novel approach to adaptive neural computation.
    • Its attractor dynamics provide insights into memory, learning, and pattern recognition.
    • Proposed sampling techniques aid in studying complex, high-dimensional neural system dynamics.