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

Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K
Learning Disabilities01:25

Learning Disabilities

585
Learning disabilities are cognitive disorders caused by neurological impairments that affect cognitive functions like language and reading, without indicating overall intellectual or developmental challenges. These disabilities differ from global intellectual or developmental disabilities as they are limited to distinct cognitive functions. Common learning disabilities include dysgraphia, dyslexia, and dyscalculia, each of which impacts unique aspects of learning.
Dyslexia
Dyslexia is a...
585
Associative Learning01:27

Associative Learning

1.3K
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...
1.3K
Purposive Learning01:22

Purposive Learning

464
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...
464
Observational Learning01:12

Observational Learning

875
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...
875
Introduction to Learning01:18

Introduction to Learning

1.0K
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...
1.0K

You might also read

Related Articles

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

Sort by
Same author

Universal scale laws for colors and patterns in imagery.

Journal of the Optical Society of America. A, Optics, image science, and vision·2025
Same author

Field Theoretical Approach for Signal Detection in Nearly Continuous Positive Spectra I: Matricial Data.

Entropy (Basel, Switzerland)·2021
Same author

Field Theoretical Approach for Signal Detection in Nearly Continuous Positive Spectra II: Tensorial Data.

Entropy (Basel, Switzerland)·2021
Same author

A Multiple-View Geometric Model of Specularities on Non-Planar Shapes with Application to Dynamic Retexturing.

IEEE transactions on visualization and computer graphics·2017
Same author

Image-Based Models for Specularity Propagation in Diminished Reality.

IEEE transactions on visualization and computer graphics·2017
Same author

A Geometric Model for Specularity Prediction on Planar Surfaces with Multiple Light Sources.

IEEE transactions on visualization and computer graphics·2017

Related Experiment Video

Updated: Jan 25, 2026

Qualitative and Quantitative Validation of Tools with Rating Scales Aimed at Assessing the Quality of University Service-Learning
10:39

Qualitative and Quantitative Validation of Tools with Rating Scales Aimed at Assessing the Quality of University Service-Learning

Published on: August 29, 2025

1.1K

Learning More Universal Representations for Transfer-Learning.

Youssef Tamaazousti, Herve Le Borgne, Celine Hudelot

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |May 7, 2019
    PubMed
    Summary

    This study introduces novel methods to enhance the universality of Convolutional Neural Network (CNN) representations, reducing the need for extensive annotated data. These techniques improve visual recognition across diverse tasks and domains.

    More Related Videos

    Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
    11:18

    Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

    Published on: June 1, 2015

    11.1K
    Using Learning Outcome Measures to assess Doctoral Nursing Education
    10:07

    Using Learning Outcome Measures to assess Doctoral Nursing Education

    Published on: June 21, 2010

    19.4K

    Related Experiment Videos

    Last Updated: Jan 25, 2026

    Qualitative and Quantitative Validation of Tools with Rating Scales Aimed at Assessing the Quality of University Service-Learning
    10:39

    Qualitative and Quantitative Validation of Tools with Rating Scales Aimed at Assessing the Quality of University Service-Learning

    Published on: August 29, 2025

    1.1K
    Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
    11:18

    Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

    Published on: June 1, 2015

    11.1K
    Using Learning Outcome Measures to assess Doctoral Nursing Education
    10:07

    Using Learning Outcome Measures to assess Doctoral Nursing Education

    Published on: June 21, 2010

    19.4K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Universal representations aim to encode diverse visual elements across various configurations.
    • Improving representation universality often requires costly, manually annotated data for source-task diversification.
    • Existing methods for enhancing representation universality are limited by data requirements and scope.

    Purpose of the Study:

    • To develop methods for improving the universality of Convolutional Neural Network (CNN) representations with limited annotated data.
    • To formalize the process of source-task diversification for representation enhancement.
    • To introduce a novel metric for evaluating representation universality in transfer learning.

    Main Methods:

    • Proposed two methods to enhance CNN representation universality: one leveraging human categorization knowledge, the other using fine-tuning.
    • Developed a new aggregating metric to evaluate universality within a transfer-learning framework.
    • Validated methods across 10 target classification problems in varied visual domains.

    Main Results:

    • Demonstrated significant improvements in representation universality using the proposed methods.
    • The new metric effectively captures more aspects of universality compared to previous approaches.
    • The methods proved effective on a diverse set of 10 visual classification tasks.

    Conclusions:

    • The proposed methods offer an efficient way to improve CNN representation universality without extensive manual annotation.
    • The novel evaluation metric provides a more comprehensive assessment of representation transferability.
    • These advancements contribute to more robust and versatile computer vision models.