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

Survival Tree01:19

Survival Tree

309
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
309

You might also read

Related Articles

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

Sort by
Same author

Corrigendum to "Guipi Tang alleviates vascular dementia by regulating purine metabolism via gut microbiota-derived pantothenic acid" [Phytomedicine volume 148 (2025) 157297].

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Association Between Comprehensive Health Assessment and Cardiac Mortality and All-Cause Mortality in Patients With Coronary Heart Disease.

Clinical cardiology·2026
Same author

Chromobox 3 assembles an epigenetic complex contributing to cystathionine γ-lyase-mediated protection against aortic aneurysm/dissection.

Nature communications·2026
Same author

Decadal gelatinization and phenological advancement of small jellyfish in Laizhou Bay, Bohai Sea.

Marine pollution bulletin·2026
Same author

Correction to "Catalytic Stereospecific Construction of Aminocyclopropanes from β-Boryl Amides".

Journal of the American Chemical Society·2026
Same author

Implantation of autologous strip- and columnar-shaped adipose grafts for enhanced wound healing.

The International journal of artificial organs·2026

Related Experiment Video

Updated: Dec 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

876

Short-sighted deep learning.

Ellen de Mello Koch1, Anita de Mello Koch1, Nicholas Kastanos1

  • 1School of Electrical and Information Engineering, University of the Witwatersrand, Wits 2050, South Africa.

Physical Review. E
|August 16, 2020
PubMed
Summary
This summary is machine-generated.

Deep learning

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Related Experiment Videos

Last Updated: Dec 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

876
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Area of Science:

  • Computational physics
  • Machine learning theory

Background:

  • Deep learning lacks a complete theoretical explanation.
  • Previous research links deep learning to renormalization group (RG) coarse-graining on local Ising spin lattices.

Purpose of the Study:

  • To investigate deep learning's coarse-graining capabilities on long-range Ising spin lattices.
  • To compare restricted Boltzmann machine (RBM) network flows with RG flows in this context.

Main Methods:

  • Markov-chain Monte Carlo (MCMC) simulations to determine critical temperature and scaling dimensions.
  • Training single and stacked Restricted Boltzmann Machine (RBM) networks.
  • Analyzing trained RBM weights as lattice model flows.

Main Results:

  • RBM flow for long-range Ising models did not converge to correct spin and energy scaling dimensions.
  • Stacked RBM flow showed differences in correlation functions compared to RG flow.
  • Stacked RBM flow moved towards low temperatures, unlike RG flow.

Conclusions:

  • Deep learning's coarse-graining analogy to RG may not hold for long-range spin lattices.
  • Differences in RBM and RG flows highlight limitations in current deep learning theories for complex systems.