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

Divergence and Curl01:15

Divergence and Curl

3.2K
The divergence of a vector field at a point is the net outward flow of the flux out of a small volume through a closed surface enclosing the volume, as the volume tends to zero. More practically, divergence measures how much a vector field spreads out or diverges from a given point. For an outgoing flux, conventionally, the divergence is positive. The diverging point is often called the "source" of the field. Meanwhile, the negative divergence of a vector field at a point means that the vector...
3.2K
Maxwell-Boltzmann Distribution: Problem Solving01:20

Maxwell-Boltzmann Distribution: Problem Solving

2.9K
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
2.9K
Divergence and Stokes' Theorems01:06

Divergence and Stokes' Theorems

3.7K
The divergence and Stokes' theorems are a variation of Green's theorem in a higher dimension. They are also a generalization of the fundamental theorem of calculus. The divergence theorem and Stokes' theorem are in a way similar to each other; The divergence theorem relates to the dot product of a vector, while Stokes' theorem relates to the curl of a vector. Many applications in physics and engineering make use of the divergence and Stokes' theorems, enabling us to write...
3.7K
Gene Duplication and Divergence02:37

Gene Duplication and Divergence

8.0K
The seminal work of Ohno in 1970 popularized the idea of gene duplication and divergence. DNA sequence comparison studies reveal that a large portion of the genes in bacteria, archaebacteria, and eukaryotes was  generated by gene duplication and divergence, indicating its critical role in evolution.
The duplicated copies of the gene are called Paralogs. Paralogs with similar sequences and functions form a gene family. Across several species, a large number of gene families are...
8.0K
Restriction Enzymes01:11

Restriction Enzymes

36.1K
Restriction enzymes are bacterial enzymes used to cut DNA in a sequence-specific manner. To cleave DNA, they bind to specific palindromic sequences called restriction sites. Such palindromic DNA sequences or inverted repeats are commonly found in regions of functional significance, such as the origin of replication, gene operator sites, and regions containing transcription termination signals.
The host bacteria protect their own genomic DNA from these enzymes by methylating these sites. Some...
36.1K
Machines01:19

Machines

579
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. One example of a machine is the cutting plier, which is used to cut wires by applying forces to its handles. When equal and opposite forces are exerted on the handles of the cutting plier, they cause the cutting edges to come together and apply equal and opposite reaction forces on the wire, which are greater than the applied forces.
A free-body diagram of the...
579

You might also read

Related Articles

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

Sort by
Same author

A curated reference database of membrane-permeability annotations for biological dyes.

Scientific data·2026
Same author

Copper-Iron Cell Death Axis: Mechanistic Crosstalk, Disease Implications and an Integrated Metallo-Redox-Metabolic Framework.

International journal of biological sciences·2026
Same author

Rethinking bioinformatics in liquid-liquid phase separation: data resources, predictive models, and an event-centric perspective.

Briefings in bioinformatics·2026
Same author

SP1 antagonizes H3K27me3 to shape chromatin landscapes for RNA polymerase II recruitment during gastrulation.

Nucleic acids research·2026
Same author

ZJU index and the prevalence of kidney stones in US adults: evidence from NHANES 2007-2018.

BMC urology·2026
Same author

Synthesis, swelling behavior and performance characterization of carboxymethylated Artemisia sphaerocephala Krasch gum-based superabsorbent polymers.

Plant physiology and biochemistry : PPB·2026

Related Experiment Video

Updated: Feb 4, 2026

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

7.5K

LCD: A Fast Contrastive Divergence Based Algorithm for Restricted Boltzmann Machine.

Lin Ning1, Randall Pittman1, Xipeng Shen1

  • 1North Carolina State University, Raleigh, NC, United States.

Neural Networks : the Official Journal of the International Neural Network Society
|October 2, 2018
PubMed
Summary

Lean Contrastive Divergence (LCD) accelerates Restricted Boltzmann Machine (RBM) learning and prediction. This novel algorithm uses bounds-based filtering and delta product to significantly speed up RBMs without altering outcomes.

Keywords:
AccelerationContrastive DivergenceRBM

More Related Videos

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.5K
High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal
06:24

High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal

Published on: October 31, 2019

6.9K

Related Experiment Videos

Last Updated: Feb 4, 2026

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

7.5K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.5K
High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal
06:24

High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal

Published on: October 31, 2019

6.9K

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Deep Learning

Background:

  • Restricted Boltzmann Machines (RBMs) are foundational for deep learning models.
  • Efficient learning and prediction are critical for practical RBM applications.

Purpose of the Study:

  • To introduce Lean Contrastive Divergence (LCD), a modified algorithm for RBMs.
  • To accelerate RBM training and prediction speed without compromising accuracy.

Main Methods:

  • Developed LCD by incorporating bounds-based filtering and delta product optimizations.
  • Bounds-based filtering replaces vector dot products with faster calculations using triangle inequality.
  • Delta product identifies and eliminates redundant computations within Gibbs Sampling.

Main Results:

  • Achieved significant speedups in RBM learning and prediction.
  • Demonstrated up to 3X speedup for training and 5.3X for prediction.
  • Optimizations are compatible with standard Contrastive Divergence and its variants.

Conclusions:

  • LCD offers a computationally efficient approach to RBMs.
  • The proposed optimizations are suitable for implementation on massively parallel processors.
  • LCD enhances the practical utility of RBMs in deep learning.