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 Concept Videos

Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Reducing Line Loss01:18

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Training thermodynamic computers by gradient descent.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Impact of solvent forces and broken symmetry on the assembly of designed proteins at a liquid-solid interface.

Nature communications·2026
Same author

Nonlinear thermodynamic computing out of equilibrium.

Nature communications·2026
Same author

Learning protocols for the fast and efficient control of active matter.

Nature communications·2024
Same author

On the origin of cooperativity effects in the formation of self-assembled molecular networks at the liquid/solid interface.

Chemical science·2024
Same author

Learning stochastic dynamics and predicting emergent behavior using transformers.

Nature communications·2024

Related Experiment Video

Updated: Jul 15, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.2K

Using the Metropolis algorithm to explore the loss surface of a recurrent neural network.

Corneel Casert1, Stephen Whitelam1

  • 1Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, California 94720, USA.

The Journal of Chemical Physics
|December 16, 2024
PubMed
Summary

Metropolis Monte Carlo (MMC) training of neural networks mirrors gradient descent with Gaussian noise. MMC can probe loss function landscapes where gradient descent struggles, and optimized moves can accelerate training.

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K
Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis
06:21

Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis

Published on: September 20, 2024

711

Related Experiment Videos

Last Updated: Jul 15, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K
Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis
06:21

Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis

Published on: September 20, 2024

711

Area of Science:

  • Computational neuroscience
  • Machine learning algorithms
  • Statistical mechanics

Background:

  • The Metropolis Monte Carlo (MMC) algorithm is a computational method used for sampling from probability distributions.
  • Gradient descent is a fundamental optimization algorithm used in training machine learning models, particularly neural networks.
  • A known correspondence exists between MMC and Langevin dynamics in physical systems.

Purpose of the Study:

  • To explore the equivalence between Metropolis Monte Carlo (MMC) training and gradient descent for neural networks.
  • To investigate the behavior of MMC in regimes where gradient descent faces challenges.
  • To demonstrate the potential of MMC for accelerating neural network training.

Main Methods:

  • Analyzing the mathematical equivalence between small-step MMC and gradient descent with Gaussian white noise.
  • Applying MMC to train a simple recurrent neural network.
  • Examining MMC performance in regions of large and small loss function gradients.
  • Designing custom Monte Carlo trial moves for neural network weights.

Main Results:

  • Small-step MMC on neural network weights is equivalent to gradient descent with Gaussian noise.
  • MMC effectively trains neural networks even when gradients are very large or small, unlike standard gradient descent.
  • Purposefully designed MMC moves can accelerate neural network training.

Conclusions:

  • Metropolis Monte Carlo offers a viable alternative and complementary approach to gradient descent for neural network training.
  • MMC can serve as a valuable tool for analyzing neural network loss landscapes in challenging regimes.
  • Optimized Monte Carlo methods hold promise for improving training efficiency in deep learning.