Example: dental hygienist
Understanding deep learning requires rethinking …

Understanding deep learning requires rethinking …

Back to document page

Bartlett (1998) proved bounds on the fat shattering dimension of multilayer perceptrons with sig-moid activations in terms of the `1-norm of the weights at each node. This important result gives a generalization bound for neural nets that is independent of the network size. However, for RELU networks the `1-norm is no longer informative. This ...

  Learning, Deep, Requires, Shattering, Deep learning requires

Download Understanding deep learning requires rethinking …


Information

Domain:

Source:

Link to this page:

Please notify us if you found a problem with this document:

Other abuse

Advertisement

Related search queries