Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Human semi-supervised learning.

Bryan R Gibson¹, Timothy T Rogers, Xiaojin Zhu

¹Department of Computer Sciences, University of Wisconsin-Madison, WI 53706-1685, USA. bgibson@cs.wisc.edu

Topics in Cognitive Science

|January 22, 2013

Summary

This summary is machine-generated.

Related Concept Videos

Observational Learning

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

Large Language Models Estimate Fine-Grained Human Color-Concept Associations.

Cognitive science·2026

Same author

All spectral frequencies of neural activity reveal semantic representation in the human anterior ventral temporal cortex.

Imaging neuroscience (Cambridge, Mass.)·2026

Same author

Generating LGE/CGE Organoids from Human Pluripotent Stem Cell-derived Brain Organoids Without External Signal Induction.

Cell reports·2026

Same author

AI-Enhanced Semantic Feature Norms for 786 Concepts.

Topics in cognitive science·2025

Same author

Efficacy of bilateral soft exoskeleton training for people with subacute stroke: a randomized controlled trial.

Journal of neuroengineering and rehabilitation·2025

Same author

Representational similarity learning reveals a graded multidimensional semantic space in the human anterior temporal cortex.

Imaging neuroscience (Cambridge, Mass.)·2025

Same journal

Limits to Language Prediction: Findings From Diverse Populations.

Topics in cognitive science·2026

Same journal

There Is More Than Meets the Eye: The Dual Role of Perception in Shaping Color Lexicons.

Topics in cognitive science·2026

Same journal

Inference and Imagination.

Topics in cognitive science·2026

Same journal

Gesture Use Across Different Concepts: Focusing on Cross-Linguistic Diversity.

Topics in cognitive science·2026

Same journal

Exploring Amazonian Cognitive Diversity at Chana Research Station.

Topics in cognitive science·2026

Same journal

Do (We Think That) Plants Have Agency?

Topics in cognitive science·2026

See all related articles

This study shows that semi-supervised learning, which uses both labeled and unlabeled data, effectively models human categorization behavior. These findings bridge machine learning and cognitive science, offering new insights into how humans learn categories.

Area of Science:

Cognitive Science
Machine Learning
Artificial Intelligence

Background:

Human categorization research often focuses on fully supervised or unsupervised learning.
Real-world learning is typically semi-supervised, involving abundant unlabeled data and occasional labeled examples.

Purpose of the Study:

To explore the application of machine learning's semi-supervised techniques to human categorization learning.
To investigate how combining labeled and unlabeled data can explain human learning behavior.

Main Methods:

Leveraging equivalences between human categorization models and machine learning algorithms.
Designing and conducting experiments with human participants exposed to semi-supervised learning conditions.

Main Results:

Related Experiment Videos

Semi-supervised learning models accurately explain human categorization performance with mixed data types.
Demonstrated the utility of machine learning approaches in cognitive modeling.

Conclusions:

Semi-supervised learning provides a powerful framework for understanding human category acquisition.
Highlights the potential for cross-disciplinary insights between AI and cognitive science, while noting areas for future research.