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

Reducing Line Loss01:18

Reducing Line Loss

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...
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
Comparing Experimental Results: Student's t-Test01:09

Comparing Experimental Results: Student's t-Test

The t-test is a statistical method used to compare the sample mean with a population mean or compare two means from two data sets. The test statistic is calculated from the standard deviation, mean, and number of measurements in the data set at a selected confidence interval and then compared to a table of critical values at this confidence level. If the test statistic is smaller than the critical value, the null hypothesis is accepted. In this case, we state that the difference between the...
Introduction to Learning01:18

Introduction to Learning

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...
Line Loss01:10

Line Loss

The different configurations of source-load connections include wye (star) and delta connections. The relationship between line and phase voltages and currents varies depending on the configuration. When the source is supplying power, it is transmitted through the wires to the load, and during this transmission, some power is absorbed by the wires, leading to line loss.
Line loss impacts power delivery efficiency in a balanced three-phase circuit. The symmetry in such a circuit simplifies the...

You might also read

Related Articles

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

Sort by
Same author

Approximation rates in Besov norms and sample-complexity of Kolmogorov-Arnold networks with residual connections.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Comparison of the Efficacy of 35 Anticancer Drugs According to Genomic Profiling and Biological Characteristics of 14 Gastric Cancer Cell Lines.

International journal of molecular sciences·2026
Same author

Correction: Multicenter phase Ib/II study of second-line durvalumab and tremelimumab in combination with paclitaxel in patients with biomarker-selected metastatic gastric cancer.

British journal of cancer·2025
Same author

WNT4 deficiency impacts heart, diaphragm, and palate development: Insights from human genetics, machine learning, and mouse models.

Developmental biology·2025
Same author

Cryopreservation of Bulk-Produced Primary Rat Oligodendrocyte Progenitor Cells.

Bio-protocol·2025
Same author

Risk of pancreatic cancer according to glycemic status in nonalcoholic fatty liver disease: a nationwide cohort study.

Scientific reports·2025
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Videos

Temperature-free loss function for contrastive learning.

Bum Jun Kim1, Sang Woo Kim2

  • 1Graduate School of Engineering, The University of Tokyo, Tokyo, 113-8656, Japan.

Neural Networks : the Official Journal of the International Neural Network Society
|June 10, 2026
PubMed
Summary
This summary is machine-generated.

Researchers developed a novel contrastive learning method that eliminates the need for temperature tuning in InfoNCE loss. This innovation simplifies the process and improves performance by addressing gradient descent issues.

Keywords:
Contrastive learningGradient descent optimizationHyperparameter tuningInfoNCE lossSelf-supervised learningTemperature

Related Experiment Videos

Area of Science:

  • Artificial Intelligence
  • Machine Learning

Background:

  • Contrastive learning is a key self-supervised learning technique.
  • InfoNCE loss is a common method for representation learning in contrastive learning.
  • InfoNCE loss requires a temperature hyperparameter that is difficult to tune.

Purpose of the Study:

  • To propose a novel method for deploying InfoNCE loss without temperature.
  • To improve the ease of use and performance of contrastive learning.

Main Methods:

  • Replaced temperature scaling in InfoNCE loss with the inverse hyperbolic tangent function.
  • Developed a modified InfoNCE loss for hyperparameter-free deployment.
  • Conducted theoretical analysis on gradient properties.

Main Results:

  • The proposed method enables temperature-free deployment of InfoNCE loss.
  • Achieved performance gains in contrastive learning tasks.
  • Demonstrated desirable gradient properties compared to standard InfoNCE loss.
  • Validated on five contrastive learning benchmarks.

Conclusions:

  • The novel approach simplifies contrastive learning by removing temperature tuning.
  • The method offers improved performance and desirable gradient characteristics.
  • This work presents a significant advancement for practical self-supervised representation learning.