🏢 Oregon State University
Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
·2347 words·12 mins·
loading
·
loading
🏢 Oregon State University
Crowd wisdom solves noisy label learning!
Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
·2736 words·13 mins·
loading
·
loading
AI Generated
Multimodal Learning
Cross-Modal Retrieval
🏢 Oregon State University
Unaligned multimodal mixtures’ shared components are identifiable under mild conditions using a distribution-matching approach, relaxing assumptions of existing methods.
Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
·3150 words·15 mins·
loading
·
loading
Machine Learning
Deep Learning
🏢 Oregon State University
Boosting Bayesian deep learning’s diversity and uncertainty quantification, this study proposes hyperspherical energy minimization of CKA to generate diverse and reliable neural network ensembles and …