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 Video

Updated: Jun 15, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Memory dynamics in attractor networks with saliency weights.

Huajin Tang1, Haizhou Li, Rui Yan

  • 1Institute for Infocomm Research, Agency for Science Technology and Research, Singapore 138632. htang@i2r.a-star.edu.sg

Neural Computation
|March 19, 2010
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

Dendritic nonlinearities mitigate communication costs.

Patterns (New York, N.Y.)·2026
Same author

Closed-loop correction reprogramming for fine-grained visual prompting.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Artificial plateau neurons with in-situ spike-malleability for rhythmic quadrupedal locomotion.

Nature communications·2026
Same author

SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning.

IEEE transactions on neural networks and learning systems·2025
Same author

Geo-GCN: Geometric-Graphical Convolutional Network for EEG-based Auditory Attention Detection.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

CA-NeuroSpex: Context-Informed Autoregressive Neuro-Guided Speaker Extraction.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study explores how correlated memories are represented in biological neural networks. Saliency weights influence memory retrieval, showing graded-response neurons reduce spurious states compared to binary neurons.

Area of Science:

  • Computational neuroscience
  • Theoretical neuroscience
  • Neural network modeling

Background:

  • Attractor neural networks (ANNs) model memory processes like encoding, storage, and retrieval.
  • Traditional models often use uncorrelated patterns in binary networks, limiting biological plausibility.
  • Understanding correlated memory representations is crucial for realistic neural network models.

Purpose of the Study:

  • To investigate neuronal representations of correlated memory patterns in a biologically plausible attractor network.
  • To examine the role of saliency weights in memory dynamics and retrieval.
  • To compare the performance of graded-response neurons versus binary neurons in handling correlated memories.

Main Methods:

  • Utilized a biologically plausible attractor neural network model.

Related Experiment Videos

Last Updated: Jun 15, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Analyzed the dynamics of correlated memory patterns.
  • Investigated the impact of saliency weights on attractor landscapes and memory convergence.
  • Compared network performance using graded-response neurons versus binary neurons.

    • Main Results:

    • Memory retrieval dynamics are significantly influenced by saliency distribution, affecting attractor landscapes.
    • Established conditions for network convergence to unique or multiple memories.
    • Demonstrated that graded-response neurons outperform binary neurons by reducing spurious states.
    • Showed that nonuniform saliency distributions can eliminate spurious states.

    Conclusions:

    • Saliency weights play a critical role in the retrieval and stability of correlated memories in neural networks.
    • Graded-response neurons offer advantages over binary neurons for representing complex memory patterns, reducing network errors.
    • The findings provide insights into the computational principles of memory in biological and artificial systems.