Interactive Machine Learning

GPTKB entity

Statements (49)
Predicate Object
gptkbp:instanceOf Machine Learning Paradigm
gptkbp:appliesTo gptkb:Unsupervised_Learning
gptkb:Reinforcement_Learning
Supervised Learning
Semi-supervised Learning
gptkbp:benefit Faster Model Adaptation
Improved User Trust
Reduced Data Requirements
gptkbp:challenge Scalability
Interface Design
Bias Introduction
User Fatigue
gptkbp:characteristic User Interaction
Human-in-the-loop
Iterative Feedback
gptkbp:conference gptkb:CHI
gptkb:AAAI
gptkb:ICML
gptkb:NeurIPS
gptkbp:distinctFrom Traditional Machine Learning
gptkbp:enables Personalization
Active Learning
Model Refinement
gptkbp:fieldOfStudy gptkb:Machine_Learning
gptkb:artificial_intelligence
gptkbp:firstDescribed Early 2000s
gptkbp:goal Improve Model Performance with User Feedback
Increase Usability of ML Systems
Reduce Annotation Cost
https://www.w3.org/2000/01/rdf-schema#label Interactive Machine Learning
gptkbp:notableContributor gptkb:James_Fogarty
Daniel S. Weld
Saleema Amershi
gptkbp:notablePublication Amershi et al., 2014, 'Power to the People: The Role of Humans in Interactive Machine Learning'
Ware et al., 2001, 'Interactive Machine Learning for Data Visualization'
Fails and Olsen, 2003, 'Interactive Machine Learning'
gptkbp:relatedTo gptkb:Human-Computer_Interaction
gptkb:Reinforcement_Learning
Active Learning
gptkbp:requires User Feedback
Iterative Model Updates
gptkbp:usedIn gptkb:Computer_Vision
gptkb:Natural_Language_Processing
Recommendation Systems
Data Labeling
Interactive Data Analysis
Personalized Systems
gptkbp:bfsParent gptkb:IML
gptkbp:bfsLayer 7