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

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...
Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

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...
Cognitive Learning01:21

Cognitive Learning

Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Purposive Learning01:22

Purposive Learning

E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a bonus...
Observational Learning01:12

Observational Learning

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 because...

You might also read

Related Articles

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

Sort by
Same author

Study on Mechanical Properties and Synergistic Mechanism of Concrete Reinforced with Hybrid Basalt Fibers of Different Lengths.

Materials (Basel, Switzerland)·2026
Same author

Reduced mechanical strength correlates with decreased elastin content in aortic intima-media tissue: association with dissection in human ascending aortas.

Medical & biological engineering & computing·2026
Same author

Sustainable and High-Performance Polylactide/Polycarbonate Blends with Enhanced Toughness and Thermal Stability via Stereocomplexation and Phase Continuity.

Polymer science & technology (Washington, D.C.)·2026
Same author

Redox-active covalent organic framework electrolyte modulates interfacial Li<sup>+</sup> deposition for stable solid-state lithium metal batteries.

Journal of colloid and interface science·2026
Same author

Dissecting Immune Cell Ferroptosis via Single-Cell Multi-Omics Identifies RPL8 as a Potential Therapeutic Target for Depression.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026
Same author

Non-target divergence hypothesis: Toward understanding modality differences in cross-modal knowledge distillation.

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

Related Experiment Videos

Diverse Teacher-Students for deep safe semi-supervised learning under class mismatch.

Qikai Wang1, Rundong He1, Yongshun Gong1

  • 1School of Software, Shandong University, China.

Neural Networks : the Official Journal of the International Neural Network Society
|March 28, 2025
PubMed
Summary

Diverse Teacher-Students (DTS) framework uses dual models to improve semi-supervised learning. It effectively handles unseen-class data, boosting classification accuracy for seen classes and unseen class detection.

Keywords:
Safe semi-supervised learningSemi-supervised learningTeacher–student

Related Experiment Videos

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Semi-supervised learning (SSL) enhances model performance using unlabeled data, crucial when labeled data is scarce.
  • Unlabeled datasets often contain unseen-class samples, negatively impacting seen-class classification.
  • Current safe SSL methods struggle with simultaneous seen-class classification and unseen-class detection due to single-model training conflicts.

Purpose of the Study:

  • To introduce a novel framework, Diverse Teacher-Students (DTS), to address limitations in current safe SSL methods.
  • To effectively handle unseen-class samples in unlabeled data for improved classification and detection.
  • To enhance model optimization by separating the tasks of classification and detection.

Main Methods:

  • The DTS framework employs dual teacher-student models for distinct task handling.
  • A novel uncertainty score is utilized to differentiate seen-class and unseen-class samples.
  • An additional (K+1)th class supervisory signal is generated for comprehensive training.

Main Results:

  • DTS demonstrates superior performance over baseline methods across diverse datasets and configurations.
  • The dual-model approach effectively enhances seen-class classification accuracy.
  • Unseen-class detection is significantly improved compared to existing methods.

Conclusions:

  • The DTS framework offers an effective solution for semi-supervised learning with unseen-class data.
  • Separating classification and detection tasks in dual teacher-student models optimizes training.
  • DTS provides a robust and versatile approach for improving SSL performance.