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

Sample Size Calculation01:19

Sample Size Calculation

6.1K
Knowledge of the sample size is the first requirement to conduct random sampling or an experiment. The sample size is the total number of units, observations, or groups (in some cases) used to get the data to estimate a population parameter. As the name suggests, the sample size is that of the sample drawn from the population and differs from the population size.
The sample size for the given experiment or sampling effort is fundamental to any study design. Sample size decides the number of...
6.1K
Sampling Methods: Overview01:06

Sampling Methods: Overview

2.0K
A sample refers to a smaller subset representative of a larger population. In analytical chemistry, studying or analyzing an entire population is often impractical or impossible. Therefore, samples are used to draw inferences and generalize the whole population. The sampling method selects individuals or items from a population to create a sample. Standard sampling methods include random, judgemental, systematic, stratified, and cluster sampling. 
In analytical chemistry, the choice of...
2.0K
Sampling Methods: Sample Types01:18

Sampling Methods: Sample Types

1.8K
Sampling materials are classified into three main types: solid, liquid, and gas.
Solid samples include a variety of substances, such as sediments from water bodies, soil, metals, and biological tissues. Two standard methods for extracting sediments from water bodies are grab sampling and piston coring. Grab sampling involves using a device to collect a discrete sediment sample from the bottom of a water body with minimal disturbance. Grab samples do not always represent the entire area due to...
1.8K
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

759
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...
759
Downsampling01:20

Downsampling

548
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
548
Reducing Line Loss01:18

Reducing Line Loss

317
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...
317

You might also read

Related Articles

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

Sort by
Same author

White matter reflects the childhood exposome.

bioRxiv : the preprint server for biology·2026
Same author

Mapping the spatiotemporal continuum of structural connectivity development across the human connectome in youth.

Nature communications·2026
Same author

Successful Management of Recurrent Hemoptysis, Polycythemia and Respiratory Distress in a Dog.

Animals : an open access journal from MDPI·2026
Same author

Long-term follow-up of bronchomalacia after bronchoscopy: survival and prognostic factors in dogs.

Journal of veterinary internal medicine·2026
Same author

Reproducibility of Diffusion, Shape, and Connectivity Metrics Across Scanners: Implications for Multi-Site Tractography.

bioRxiv : the preprint server for biology·2026
Same author

Tractometry-Based Quantification of Along-Tract White-Matter Hemispheric Asymmetry in Alzheimer's Disease.

bioRxiv : the preprint server for biology·2026

Related Experiment Video

Updated: Dec 30, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Structural Analysis and Optimization of Convolutional Neural Networks with a Small Sample Size.

Rhett N D'souza1, Po-Yao Huang2, Fang-Cheng Yeh3

  • 1Department of Electrical Engineering and Computer Science, McCormick School of Engineering and Applied Science, Northwestern University, Evanston, IL, USA.

Scientific Reports
|January 23, 2020
PubMed
Summary

Optimizing deep neural network structure is crucial for small data challenges, outperforming random selection. Network structure is data-driven, not sample-size driven, improving accuracy in medical imaging and other domains.

Related Experiment Videos

Last Updated: Dec 30, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Deep neural networks (DNNs) excel in Big Data but struggle with limited training samples, a common issue in fields like medical imaging, leading to overfitting.
  • The
  • Small Data
  • paradigm requires different strategies than traditional Big Data approaches.

Purpose of the Study:

  • To investigate the influence of network structure on DNN performance under small data conditions.
  • To determine if optimal network structure depends more on sample size or data characteristics.
  • To assess the impact of structural optimization on accuracy in limited-data scenarios.

Main Methods:

  • Systematically explored all layer combinations within a VC-dimension bound to analyze structural hyperparameter effects.
  • Evaluated performance across datasets with varying sample sizes (100, 500, 1,000) and data types (photographic, calligraphic, medical).
  • Compared accuracy of optimized network structures against random selection.

Main Results:

  • Structural optimization significantly improved accuracy, with gains of 27.99%, 16.44%, and 13.11% for sample sizes of 100, 500, and 1,000, respectively, on the MNIST dataset.
  • Optimal network structure was primarily dictated by data nature (e.g., photographic, medical) rather than sample size.
  • Achieved high accuracy (e.g., 91.13% with 500 samples on MNIST, 94.10% with 3,300 samples on Mitosis dataset) post-optimization.

Conclusions:

  • Network structure is a critical factor for addressing the
  • Small Data
  • challenge in deep learning.
  • Data-driven optimization of network architecture is more effective than relying solely on sample size.
  • Optimized DNNs demonstrate strong performance even with limited datasets, particularly in specialized domains like medical imaging.