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

Recurrent sampling models for the Helmholtz machine.

P Dayan1

  • 1Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139, USA. dayan@ai.mit.edu

Neural Computation
|March 23, 1999
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

Knowing me, knowing you: Interpersonal similarity improves predictive accuracy and reduces attributions of harmful intent.

Cognition·2022
Same author

Disrupted habenula function in major depression.

Molecular psychiatry·2016
Same author

The specificity of Pavlovian regulation is associated with recovery from depression.

Psychological medicine·2016
Same author

Memory, modelling and Marr: a commentary on Marr (1971) 'Simple memory: a theory of archicortex'.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2015
Same author

How receptor diffusion influences gradient sensing.

Journal of the Royal Society, Interface·2015
Same author

The influence of receptor positioning on chemotactic information.

Journal of theoretical biology·2014
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 introduces new models for cortical processing that capture dependencies within layers, moving beyond simplified independence assumptions. This enhances understanding of neural network learning and information processing.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Artificial intelligence

Background:

  • Current density estimation models for cortical learning often assume unit independence within layers.
  • This assumption simplifies models but may not accurately reflect neural processing.

Purpose of the Study:

  • To propose and develop novel architectures that explicitly model dependencies within layers.
  • To enhance the realism and accuracy of analysis-by-synthesis models for cortical processing.

Main Methods:

  • Utilizing Markov random fields to capture intra-layer dependencies.
  • Developing alternative stochastic sampling architectures.
  • Implementing and testing these architectures within real and binary Helmholtz machines.
  • Employing recurrent sampling for generative and recognition models.

Related Experiment Videos

Main Results:

  • Demonstrated the feasibility of incorporating intra-layer dependencies using Markov random fields and recurrent sampling.
  • Showcased the application of these methods within Helmholtz machine frameworks.
  • Provided a more nuanced approach to modeling neural information processing.

Conclusions:

  • Explicitly modeling intra-layer dependencies offers a more accurate representation of cortical processing.
  • The proposed Markov random field and recurrent sampling methods provide a flexible framework for advanced neural network modeling.
  • These advancements contribute to a deeper understanding of learning and processing in biological and artificial neural systems.