Abstrakti

Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that mitigates these issues by converting NNs from weight space to function space, via a dual parameterization. Importantly, the dual parameterization enables us to formulate a sparse representation that captures information from the entire data set. This offers a compact and principled way of capturing uncertainty and enables us to incorporate new data without retraining whilst retaining predictive performance. We provide proof-of-concept demonstrations with the proposed approach for quantifying uncertainty in supervised learning on UCI benchmark tasks.
AlkuperäiskieliEnglanti
Sivumäärä6
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiEi oikeutettu
TapahtumaWorkshop on Duality Principles for Modern Machine Learning - Honolulu, Yhdysvallat
Kesto: 29 heinäk. 202329 heinäk. 2023
https://icml.cc/virtual/2023/workshop/21496

Workshop

WorkshopWorkshop on Duality Principles for Modern Machine Learning
Maa/AlueYhdysvallat
KaupunkiHonolulu
Ajanjakso29/07/202329/07/2023
www-osoite

Sormenjälki

Sukella tutkimusaiheisiin 'Sparse Function-space Representation of Neural Networks'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä