A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs.

Gadi Naveh Zohar Ringel

Published in: NeurIPS (2021)

Keyphrases

gaussian processes
multi task learning
learning algorithm
multitask learning
bayesian methods
preference learning
learning process
learning problems
supervised learning
bayesian framework
gaussian process regression
gaussian process
multi task
learning tasks
higher order
active learning
feature vectors