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

3.3K
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...
3.3K
Reducing Line Loss01:18

Reducing Line Loss

447
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...
447
Introduction to Learning01:18

Introduction to Learning

1.6K
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
1.6K
Deconvolution01:20

Deconvolution

695
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
695
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

1.2K
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
1.2K
Survival Tree01:19

Survival Tree

497
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...
497

You might also read

Related Articles

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

Sort by
Same author

Intermolecular hydrogen-bonding effects on excited-state competition for near-unity emission in copper(I) iodide hybrids with cationic ligands.

Dalton transactions (Cambridge, England : 2003)·2026
Same author

The Effect of mascRNA on the Phenotype Transition and Mitophagy in Vascular Smooth Muscle Cells Exposed to Hypoxia.

Current molecular medicine·2026
Same author

A Room-Temperature Rh-Catalyzed Kinetic Resolution Pathway for Expedient Access to <i>P</i>‑Stereogenic Cyclic Phosphinates.

JACS Au·2026
Same author

Bandgap Engineering of Copper(I) Iodide Hybrid Materials for NIR-II Emission and Photocatalytic H<sub>2</sub>O<sub>2</sub> Production.

Inorganic chemistry·2026
Same author

Curcumin inhibits the proliferation of diffuse large B-cell lymphoma by inducing ferroptosis via the ACSL4-SAT1-GPX4 axis.

Translational cancer research·2026
Same author

The clinical trial landscape of osteosarcoma: integrating trial data, immunotherapeutic trends, and biomarker insights.

Frontiers in immunology·2026

Related Experiment Video

Updated: Apr 5, 2026

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.2K

Towards dropout training for convolutional neural networks.

Haibing Wu1, Xiaodong Gu1

  • 1Department of Electronic Engineering, Fudan University, Shanghai 200433, China.

Neural Networks : the Official Journal of the International Neural Network Society
|August 17, 2015
PubMed
Summary
This summary is machine-generated.

This study explores dropout in deep learning, particularly for convolutional neural networks. It introduces probabilistic weighted pooling as a superior alternative to max-pooling for improved model performance.

Keywords:
Convolutional neural networksDeep learningMax-pooling dropout

Related Experiment Videos

Last Updated: Apr 5, 2026

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.2K

Area of Science:

  • Deep Learning
  • Machine Learning
  • Artificial Intelligence

Background:

  • Dropout is widely used in deep learning, but its effectiveness in convolutional and pooling layers of deep convolutional neural networks remains unclear.
  • While effective in fully-connected layers, the impact of dropout on convolutional and pooling layers requires further investigation.

Purpose of the Study:

  • To investigate the effects of dropout in convolutional and pooling layers of deep convolutional neural networks.
  • To propose and validate a novel probabilistic weighted pooling method as an improvement over standard max-pooling.
  • To achieve state-of-the-art performance on benchmark datasets by optimizing dropout strategies.

Main Methods:

  • Demonstrating the equivalence of max-pooling dropout to multinomial activation sampling during training.
  • Proposing probabilistic weighted pooling for model averaging at test time.
  • Implementing and comparing dropout strategies in convolutional, pooling, and fully-connected layers.

Main Results:

  • Probabilistic weighted pooling demonstrates superior performance compared to standard max-pooling.
  • Convolutional dropout has a non-trivial effect, even with reduced overfitting in convolutional architectures.
  • Combined dropout in max-pooling and fully-connected layers achieves state-of-the-art results on MNIST and competitive results on CIFAR datasets without data augmentation.

Conclusions:

  • Probabilistic weighted pooling is a more effective approach for model averaging at test time.
  • Dropout strategies in convolutional and pooling layers significantly impact deep convolutional neural network performance.
  • Optimized dropout implementation leads to enhanced performance on image classification tasks.