Noun
A certain approach to neural networks that attempts to improve on the dropout technique. Its activation function is the maximum of the inputs.
Usage- Uncountable
- Examples
-
More examples (1)
On the acoustic side, we use a score fusion of three strong models: recurrent nets with maxout activations, very deep convolutional nets with 3x3 kernels, and bidirectional long-short term memory nets which operate on bottleneck features.