v1v2v3v4 (latest)

How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning -- an Exact Macroscopic Characterization

31 December 2021

Papers citing "How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning -- an Exact Macroscopic Characterization"

2 / 2 papers shown

Title
Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework William Andersson Jakob Heiss Florian Krach Josef Teichmann 70 2 0 24 Jul 2023
NOMU: Neural Optimization-based Model Uncertainty Jakob Heiss Jakob Weissteiner Hanna Wutte Sven Seuken Josef Teichmann BDL 92 20 0 26 Feb 2021