Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 21, 2026IEEE Transactions on Neural Networks and Learning Systems

Hybrid Transfer Active Learning for Multistream Processes With Within-Process and Cross-Process Correlation Modeling and Online Updating

View Full Paper
Ask AI
Bookmark
Share

Authors

ZHZhiyong HuCWChao Wang

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved regression accuracy in multistream processes, indicating a solution to cold-start issues.

Key Points

  • This work aims to address the cold-start problem in active learning for regression by modeling correlations between multiple streams.
  • Proposed a hybrid transfer learning framework for modeling within-process and cross-process correlations.
  • Utilized a multioutput Gaussian process covariance structure for robust prior knowledge transfer.
  • Implemented offline learning for knowledge transfer and online updating for functional relationship refinement.
  • ALR error decreases monotonically as new data is acquired, supporting the proposed framework.
  • Demonstrated superiority over benchmark methods in various numerical and real-case studies.

Cite This Study

Hu et al. (2026) studied this question.

synapsesocial.com/papers/6a377fb224f042ddf4c5a02ahttps://doi.org/10.1109/tnnls.2026.3702597
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Online Boosting Adaptive Learning under Concept Drift for Multistream Classification2024 · 26 citations
  2. 2A Bayesian Hierarchical Framework for Non-linear and Iterative Transfer Learning of Gaussian Process2026
  3. 3Active Learning Guided by Efficient Surrogate Learners2024 · 3 citations
  4. 4Amortized Active Learning for Nonparametric Functions2024
  5. 5Active Learning for Multiple Target Models2025 · 3 citations