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

Upsampling01:22

Upsampling

224
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
224
Optimal Foraging00:48

Optimal Foraging

12.0K
How animals obtain and eat their food is called foraging behavior. Foraging can include searching for plants and hunting for prey and depends on the species and environment.
12.0K
Downsampling01:20

Downsampling

148
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...
148
Law of Independent Assortment02:03

Law of Independent Assortment

55.6K
While Mendel’s Law of Segregation states that the two alleles for one gene are separated into different gametes, a different question of how different genes are inherited remains. For example, is the gene for tall plants inherited with the gene for green peas? Mendel asked this question by experimenting with a dihybrid cross; a cross in which both parents are homozygous for two distinct traits resulting in an F1 generation that are heterozygous for both traits.
55.6K
Survival Tree01:19

Survival Tree

79
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...
79
Sampling Theorem01:15

Sampling Theorem

324
In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.
324

You might also read

Related Articles

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

Sort by
Same author

Bridging Organ-on-a-Chip and Omics: A Multi-Dimensional Frontier in Biomedical Research.

Biotechnology and bioengineering·2026
Same author

Mechanical force awakens dormant catalyst: Piezocatalytic CO<sub>2</sub> reduction outperforms photocatalysis by over two orders of magnitude.

Journal of colloid and interface science·2026
Same author

Machine Learning-Assisted 3D Envelope-Enhanced SERS Platform for Detection and Classification of Multiple Coexisting Pollutants.

Analytical chemistry·2026
Same author

Personalized Dosing System Guided by Cross-Scale Metabolic Imaging Biomarkers in Neovascular Age-Related Macular Degeneration.

Translational vision science & technology·2026
Same author

What do cancer patients discuss online regarding CINV management? A social media-based topic modeling study.

Frontiers in oncology·2026
Same author

Widespread marine and freshwater distributions of active sulfoquinovose-degrading bacteria.

The ISME journal·2026
Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026
Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026
Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026
Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: Jun 21, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

685

Contrastive Unsupervised Representation Learning With Optimize-Selected Training Samples.

Yujun Cheng, Zhewei Zhang, Xuejing Li

    IEEE Transactions on Neural Networks and Learning Systems
    |July 12, 2024
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces an optimized sample selection method for contrastive unsupervised representation learning (CURL) to improve feature learning from unlabeled data. The new approach enhances accuracy and generalization by ensuring dissimilar data pairs are from different classes.

    More Related Videos

    Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
    08:56

    Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

    Published on: January 13, 2023

    2.2K
    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
    07:35

    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

    Published on: October 11, 2018

    7.5K

    Related Experiment Videos

    Last Updated: Jun 21, 2025

    Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
    03:37

    Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

    Published on: March 1, 2024

    685
    Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
    08:56

    Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

    Published on: January 13, 2023

    2.2K
    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
    07:35

    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

    Published on: October 11, 2018

    7.5K

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computer Vision

    Background:

    • Contrastive unsupervised representation learning (CURL) learns features from unlabeled data using positive and negative sample pairs.
    • Current CURL methods have limitations in the pair data generation process, impacting overall performance.
    • Optimizing sample selection is crucial for advancing unsupervised feature learning.

    Purpose of the Study:

    • To introduce an optimized pair-data sample selection method for CURL.
    • To improve the efficiency and effectiveness of generating positive and negative sample pairs.
    • To enhance the performance and generalization capabilities of CURL models.

    Main Methods:

    • Developed a novel sample selection strategy for CURL.
    • Ensured that dissimilar sample pairs are efficiently selected from different classes.
    • Conducted theoretical analysis of error probability and PAC-Bayes generalization bounds.

    Main Results:

    • The proposed method ensures that sampled data pairs (similar and dissimilar) do not belong to the same class.
    • Theoretical analysis demonstrates enhanced learning performance through reduced error probability.
    • PAC-Bayes generalization bounds are tightened compared to previous literature.
    • Numerical experiments on text and image datasets show competitive accuracy.

    Conclusions:

    • The optimized sample selection method significantly improves CURL performance.
    • The method offers better generalization bounds, crucial for robust unsupervised learning.
    • This work provides a valuable advancement for representation learning from unlabeled data.