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

Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

725
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...
725
Observational Learning01:12

Observational Learning

262
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...
262
Nonconscious Mimicry01:13

Nonconscious Mimicry

4.6K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
4.6K
Introduction to Learning01:18

Introduction to Learning

505
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...
505
Stereotype Content Model02:16

Stereotype Content Model

14.8K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.8K
Purposive Learning01:22

Purposive Learning

181
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...
181

You might also read

Related Articles

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

Sort by
Same author

TriCLFF: a multi-modal feature fusion framework using contrastive learning for spatial domain identification.

Briefings in bioinformatics·2025
Same author

An Image Information-Based Objective Assessment Method of Technical Manipulation Skills for Intravascular Interventions.

Sensors (Basel, Switzerland)·2023
Same author

Low-Density sEMG-Based Pattern Recognition of Unrelated Movements Rejection for Wrist Joint Rehabilitation.

Micromachines·2023
Same author

A Deep-Learning-Based Guidewire Compliant Control Method for the Endovascular Surgery Robot.

Micromachines·2022
Same author

SPCS: a spatial and pattern combined smoothing method for spatial transcriptomic expression.

Briefings in bioinformatics·2022
Same author

Distance correlation application to gene co-expression network analysis.

BMC bioinformatics·2022

Related Experiment Video

Updated: Aug 18, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

660

A Distinguishable Pseudo-Feature Synthesis Method for Generalized Zero-Shot Learning.

Yunpeng Jia1, Xiufen Ye1, Yusong Liu1

  • 1College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, Heilongjiang 150001, China.

Computational Intelligence and Neuroscience
|December 9, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces Distinguishable Pseudo-Feature Synthesis (DPFS) for generalized zero-shot learning (GZSL). DPFS improves classification accuracy by creating high-quality, discriminative features for both seen and unseen classes, overcoming limitations of current methods.

More Related Videos

Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.3K

Related Experiment Videos

Last Updated: Aug 18, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

660
Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.3K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Generalized zero-shot learning (GZSL) classifies both known and unknown categories.
  • Current hybrid methods using pseudo-feature synthesis face issues like negative transfer and poor class discriminability, leading to low accuracy.
  • Existing approaches struggle to effectively handle the distinct characteristics of seen and unseen classes simultaneously.

Purpose of the Study:

  • To propose a novel GZSL method, Distinguishable Pseudo-Feature Synthesis (DPFS), to enhance classification accuracy.
  • To address the problems of negative transfer and low class discriminability in existing GZSL methods.
  • To generate high-quality, distinguishable features for both seen and unseen classes.

Main Methods:

  • DPFS utilizes a pretraining step with distance prediction loss to prevent overfitting.
  • It overcomes negative transfer by selecting attributes from similar seen classes and employing sparse representations for unseen classes.
  • Pseudo-features for unseen classes are synthesized and refined by removing outliers to boost class discriminability.

Main Results:

  • DPFS generates high-quality, distinguishable characteristics for both seen and unseen classes.
  • The method effectively mitigates negative transfer by a targeted attribute selection and sparse representation strategy.
  • Experimental results on four benchmark datasets demonstrate superior GZSL classification performance compared to existing methods.

Conclusions:

  • DPFS offers a significant advancement in generalized zero-shot learning by improving feature synthesis.
  • The proposed method effectively tackles key challenges, leading to enhanced classification accuracy.
  • DPFS provides a robust framework for future research in GZSL and related areas.