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

Observational Learning01:12

Observational Learning

293
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...
293
Purposive Learning01:22

Purposive Learning

198
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...
198
Associative Learning01:27

Associative Learning

551
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...
551
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

1.9K
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...
1.9K
Introduction to Learning01:18

Introduction to Learning

523
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...
523
Reinforcement01:23

Reinforcement

319
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
319

You might also read

Related Articles

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

Sort by
Same author

An Artificial Intelligence-Driven Multimorbidity Framework Reveals a Shared Metabolic and Immune Core Across Alzheimer's Disease, Amyotrophic Lateral Sclerosis, and Frontotemporal Dementia.

Biomedicines·2026
Same author

Education, Sex, and Age Shape Rey Complex Figure Performance in Cognitively Normal Adults: An Interpretable Machine Learning Study.

Journal of clinical medicine·2025
Same author

ReduXis: A Comprehensive Framework for Robust Event-Based Modeling and Profiling of High-Dimensional Biomedical Data.

International journal of molecular sciences·2025
Same author

Comprehensive Anatomical Staging Predicts Clinical Progression in Mild Cognitive Impairment: A Data-Driven Approach.

International journal of molecular sciences·2025
Same author

TrialSieve: A Comprehensive Biomedical Information Extraction Framework for PICO, Meta-Analysis, and Drug Repurposing.

Bioengineering (Basel, Switzerland)·2025
Same author

Stratifying risk of Alzheimer's disease in healthy middle-aged individuals with machine learning.

Brain communications·2025
Same journal

Assessing the communication gap between AI models and healthcare professionals: Explainability, utility and trust in AI-driven clinical decision-making.

Artificial intelligence·2026
Same journal

Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learning.

Artificial intelligence·2023
Same journal

Learning in the Machine: Random Backpropagation and the Deep Learning Channel.

Artificial intelligence·2018
Same journal

Methods for solving reasoning problems in abstract argumentation - A survey.

Artificial intelligence·2015
Same journal

Modeling the Complex Dynamics and Changing Correlations of Epileptic Events.

Artificial intelligence·2014
Same journal

The Dropout Learning Algorithm.

Artificial intelligence·2014
See all related articles

Related Experiment Video

Updated: Sep 4, 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

676

Rule-Enhanced Active Learning for Semi-Automated Weak Supervision.

David Kartchner1,2,3, Davi Nakajima An1,2, Wendi Ren2

  • 1Laboratory for Pathology Dynamics, Georgia Institute of Technology and Emory University, Atlanta, GA 30332, USA.

Artificial Intelligence
|July 18, 2022
PubMed
Summary
This summary is machine-generated.

REGAL, a new framework for text classification, significantly reduces the need for labeled data by intelligently creating labeling functions. This approach streamlines the process, making deep learning more accessible across various domains.

Keywords:
active learningdata labelingnatural language processingtext classificationtext miningweak supervision

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

558

Related Experiment Videos

Last Updated: Sep 4, 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

676
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

558

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Natural Language Processing

Background:

  • Deep learning models require extensive labeled data, posing a significant bottleneck for new domain applications.
  • Current methods like weak supervision and active learning reduce labeling costs but still demand substantial human effort.
  • Interactive weak supervision requires users to curate labeling functions, which can be time-consuming and labor-intensive.

Purpose of the Study:

  • To introduce REGAL (Rule-Enhanced Generative Active Learning), an advanced framework for weakly supervised text classification.
  • To enhance active learning by focusing on labeling functions rather than individual data instances.
  • To significantly reduce the annotation burden associated with creating effective labeling functions for weak supervision.

Main Methods:

  • REGAL employs an active learning strategy centered on labeling functions, optimizing the creation of labeling patterns from raw text.
  • The framework enables a single annotator to label an entire dataset efficiently after initial input of just three keywords per class.
  • REGAL interactively generates high-quality labeling patterns, improving the efficiency of weak supervision.

Main Results:

  • REGAL extracts up to three times more high-accuracy labeling functions compared to state-of-the-art interactive weak supervision methods.
  • The framework dramatically decreases the annotation effort required for writing labeling functions.
  • Statistical analysis shows REGAL performs equally well or better than existing interactive weak supervision techniques on five out of six common NLP datasets.

Conclusions:

  • REGAL offers a more efficient and effective approach to weakly supervised text classification by optimizing active learning for labeling functions.
  • The framework substantially lowers the barrier to entry for applying deep learning in new domains by reducing data annotation costs.
  • REGAL represents a significant advancement in interactive weak supervision, improving scalability and performance in NLP tasks.