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

Accelerators01:17

Accelerators

288
Accelerators in concrete serve as admixtures to speed up the hardening process, enabling the concrete to achieve early strength faster. Although accelerators do not necessarily impact the time it takes concrete to set, they reduce this time in practice. A common accelerator is calcium chloride, which is particularly useful for hastening early strength development in cold weather or for rapid repair jobs that require quick heat generation after mixing.
The effectiveness of calcium chloride can...
288
Average Acceleration01:30

Average Acceleration

13.7K
The importance of understanding acceleration spans our day-to-day experiences, as well as the vast reaches of outer space and the tiny world of subatomic physics. In everyday conversation, to accelerate means to speed up. For instance, we are familiar with the acceleration of our car; the harder we apply our foot to the gas pedal, the faster we accelerate. The greater the acceleration, the greater the change in velocity over a given time. Acceleration is widely seen in experimental physics. In...
13.7K
Instantaneous Acceleration01:16

Instantaneous Acceleration

23.1K
Acceleration is in the direction of the change in velocity, but it is not always in the direction of motion. When an object slows down, its acceleration is opposite to the direction of its motion. Although commonly referred to as deceleration, this causes confusion in our analysis as deceleration is not a vector, and does not point to a specific direction with respect to a coordinate system. Therefore, the term deceleration is not used. For example, when a subway train slows down, it...
23.1K
Acceleration Vectors01:30

Acceleration Vectors

22.6K
In everyday conversation, accelerating means speeding up. Acceleration is a vector in the same direction as the change in velocity, Δv, therefore the greater the acceleration, the greater the change in velocity over a given time. Since velocity is a vector, it can change in magnitude, direction, or both. Thus acceleration is a change in speed or direction, or both. For example, if a runner traveling at 10 km/h due east slows to a stop, reverses direction, and continues their run at 10 km/h...
22.6K
Accelerating Fluids01:17

Accelerating Fluids

2.3K
When a fluid is in constant acceleration, the pressure and buoyant force equations are modified. Suppose a beaker is placed in an elevator accelerating upward with a constant acceleration, a. In the beaker, assume there is a thin cylinder of height h with an infinitesimal cross-sectional area, ΔS.
The motion of the liquid within this infinitesimal cylinder is considered to obtain the pressure difference. Three vertical forces act on this liquid:
2.3K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.6K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.6K

You might also read

Related Articles

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

Sort by
Same author

Coexistence of Synchronization and Stochasticity in Thermally Coupled Mott Oscillators.

ACS nano·2026
Same author

Erratum: "Polynomial-time solution of prime factorization and NP-complete problems with digital memcomputing machines" [Chaos 27, 023107 (2017)].

Chaos (Woodbury, N.Y.)·2026
Same author

Memory in neural activity: Long-range order without criticality.

Physical review. E·2026
Same author

Chirality-Induced Spin-Orbit Coupling and Spin Selectivity.

The journal of physical chemistry. A·2025
Same author

Mixed-mode in-memory computing: towards high-performance logic processing in a memristive crossbar array.

Communications engineering·2025
Same author

Memory-induced long-range order in dynamical systems.

Physical review. E·2025

Related Experiment Video

Updated: Feb 2, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.8K

Accelerating deep learning with memcomputing.

Haik Manukian1, Fabio L Traversa2, Massimiliano Di Ventra1

  • 1Department of Physics, University of California, San Diego, La Jolla, CA 92093, United States.

Neural Networks : the Official Journal of the International Neural Network Society
|November 21, 2018
PubMed
Summary
This summary is machine-generated.

Digital memcomputing machines (DMMs) offer an efficient alternative to contrastive divergence for training deep-belief networks. This novel approach accelerates generative pretraining and improves accuracy in pattern recognition tasks, outperforming traditional methods and quantum annealing.

Keywords:
Deep learningMemcomputingRestricted Boltzmann machines

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.6K
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K

Related Experiment Videos

Last Updated: Feb 2, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.8K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.6K
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Restricted Boltzmann machines (RBMs) and deep-belief networks are powerful neural networks used in AI and machine learning.
  • Traditional training relies on contrastive divergence (CD), an iterative unsupervised method, often followed by supervised tuning.
  • CD has limitations, including not following gradients and potentially leading to suboptimal solutions.

Purpose of the Study:

  • To introduce an efficient alternative to contrastive divergence for training RBMs.
  • To demonstrate the effectiveness of digital memcomputing machines (DMMs) in computing gradients for unsupervised training.
  • To evaluate the performance of DMMs on pattern recognition tasks using the MNIST dataset.

Main Methods:

  • Simulations of digital memcomputing machines (DMMs) were used to compute the gradient of the log-likelihood for unsupervised training.
  • The DMM approach was tested on a modified MNIST dataset for pattern recognition.
  • Comparisons were made against contrastive divergence, quantum annealing, and recent supervised training advancements (batch-normalization, rectifiers).

Main Results:

  • DMMs effectively sample the phase space of RBMs, providing near-optimal approximations.
  • The DMM method significantly reduces pretraining iterations and improves accuracy on the MNIST dataset compared to traditional methods.
  • DMMs show comparable iteration counts to quantum annealing but achieve superior training quality, outperforming it by over 1% accuracy.

Conclusions:

  • Simulating DMMs offers an efficient and effective alternative to contrastive divergence for training deep neural networks.
  • The memcomputing approach maintains a significant accuracy advantage over recent supervised training techniques.
  • This method is network-agnostic and can be extended to train more complex Boltzmann machines and deep networks.