Deep neural networks can be represented as Bayesian hierarchical models built from neuron-defined Gibbs distributions, yielding a new explanation of regularization and generalization.
Stability and generalization.Journal of Machine Learning Research, pages 499–526, 2002
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Probabilistic Representation of Deep Learning
Deep neural networks can be represented as Bayesian hierarchical models built from neuron-defined Gibbs distributions, yielding a new explanation of regularization and generalization.