The paper reviews fixed-kernel neural network theory and proposes an over-parameterized Gaussian sequence model as a prototype for feature learning.
Disentangling feature and lazy training in deep neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories
The paper reviews fixed-kernel neural network theory and proposes an over-parameterized Gaussian sequence model as a prototype for feature learning.