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

369
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...
369
Plasticity00:58

Plasticity

2.9K
Plasticity is the property where an object loses its elasticity and undergoes irreversible deformation, even after the deformation forces are eliminated. If a material deforms irreversibly without increasing stress or load, then this is called ideal plasticity. For example, when a force is applied to an aluminum rod, it changes its shape, but it does not return to its original shape once the force is removed. Plastic deformation or ductility is thus a permanent deformation or change in the...
2.9K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.5K
3.5K
Improving Translational Accuracy02:07

Improving Translational Accuracy

14.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.0K
Observational Learning01:12

Observational Learning

791
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
791
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

1.3K
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
1.3K

You might also read

Related Articles

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

Sort by
Same author

Genotype characteristics and immunological indicator evaluation of 311 hemophagocytic lymphohistiocytosis cases in China.

Orphanet journal of rare diseases·2020
Same author

Metabolic Fingerprinting on Synthetic Alloys for Medulloblastoma Diagnosis and Radiotherapy Evaluation.

Advanced materials (Deerfield Beach, Fla.)·2020
Same author

FADS1 promotes the progression of laryngeal squamous cell carcinoma through activating AKT/mTOR signaling.

Cell death & disease·2020
Same author

Effect of monochromatic light on the temporal expression of <i>N-acetyltransferase</i> in chick pineal gland.

Chronobiology international·2020
Same author

NCAPG Is a Promising Therapeutic Target Across Different Tumor Types.

Frontiers in pharmacology·2020
Same author

A Tool for Early Prediction of Severe Coronavirus Disease 2019 (COVID-19): A Multicenter Study Using the Risk Nomogram in Wuhan and Guangdong, China.

Clinical infectious diseases : an official publication of the Infectious Diseases Society of America·2020

Related Experiment Video

Updated: Jan 8, 2026

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
07:31

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

7.2K

CSCL: Bridging the plasticity-stability gap in continuous supervised contrastive learning.

Yi Xiong1, Liqi Xiang2, Qianyue Cao1

  • 1School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China; Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, 215123, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 21, 2025
PubMed
Summary

This study introduces Continual Supervised Contrastive Learning (CSCL) to improve continual learning (CL) by enhancing plasticity and stability. CSCL uses novel methods to boost performance in non-stationary data streams.

Keywords:
Catastrophic forgettingContinual learningContrastive learningRepresentation knowledge

More Related Videos

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.0K

Related Experiment Videos

Last Updated: Jan 8, 2026

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
07:31

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

7.2K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.0K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Continual Learning (CL) addresses non-stationary data streams, enabling models to learn new information without forgetting prior knowledge.
  • Supervised Contrastive Learning (SCL) has shown promise in enhancing CL performance, particularly in improving resistance to forgetting.
  • However, SCL-based CL models still face challenges with learning plasticity and memory stability in their representation space.

Purpose of the Study:

  • To propose a novel framework, Continual Supervised Contrastive Learning (CSCL), to address the limitations of SCL in continual learning.
  • To enhance adaptability to new tasks and retain knowledge of previously learned tasks within the CL process.
  • To theoretically investigate and practically improve the underlying reasons for SCL's effectiveness in CL.

Main Methods:

  • Introduced Continual Supervised Contrastive Learning (CSCL) framework.
  • Incorporated the De-redundant Interpolation Method to improve negative sample diversity and learning plasticity for new classes.
  • Implemented the Magnetic Force Method to ensure inter-class separation and intra-class aggregation, enhancing memory stability for old classes.

Main Results:

  • CSCL framework demonstrated advanced performance on popular benchmark image classification datasets.
  • The De-redundant Interpolation Method and Magnetic Force Method significantly boosted classification accuracy, ranging from 2.20 to 15.56 points.
  • These methods proved flexible as plug-ins for existing SCL-based CL frameworks.

Conclusions:

  • CSCL effectively enhances both learning plasticity and memory stability in continual learning settings.
  • The proposed De-redundant Interpolation and Magnetic Force Methods offer significant improvements and are adaptable components for SCL-based CL.
  • CSCL represents a significant advancement in enabling models to learn continuously while retaining previously acquired knowledge.