Multiple-boundary clustering and prioritization to promote neural network retraining

With the increasing application of deep learning (DL) models in many safety-critical scenarios, effective and efficient DL testing techniques are much in demand to improve the quality of DL models. One of the major challenges is the data gap between the training data to construct the models and the...

Full description

Saved in:
Bibliographic Details
Main Authors: Shen, Weijun, Li, Yanhui, Chen, Lin, Han, Yuanlei, Zhou, Yuming, Xu, Baowen
Format: Conference Proceeding
Language:English
Subjects:
Computing methodologies
Computing methodologies > Machine learning
Computing methodologies > Machine learning > Learning paradigms
Computing methodologies > Machine learning > Learning paradigms > Unsupervised learning
Computing methodologies > Machine learning > Learning paradigms > Unsupervised learning > Cluster analysis
Computing methodologies > Machine learning > Machine learning approaches
Computing methodologies > Machine learning > Machine learning approaches > Neural networks
Context modeling
Data models
Deep learning
Information systems
Information systems > Information systems applications
Information systems > Information systems applications > Data mining
Labeling
Multiple-Boundary
Neural network
Retraining
Software and its engineering
Software and its engineering > Software creation and management
Software and its engineering > Software creation and management > Software verification and validation
Software and its engineering > Software creation and management > Software verification and validation > Software defect analysis
Software testing
Task analysis
Testing
Theory of computation
Theory of computation > Theory and algorithms for application domains
Theory of computation > Theory and algorithms for application domains > Machine learning theory
Theory of computation > Theory and algorithms for application domains > Machine learning theory > Unsupervised learning and clustering
Training
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!