rectifiedLinearUnit: Rectified linear unit function with unit derivatives.

In darch: Package for Deep Architectures and Restricted Boltzmann Machines

Description

The function calculates the activation of the units and returns a list, in which the first entry is the rectified linear activation of the units and the second entry is the derivative of the transfer function.

Usage

rectifiedLinearUnit(input, ...)

Arguments

input	Input for the activation function.
...	Additional parameters, not used.

Value

A list with the rectified linear activation in the first entry and the derivative of the activation in the second entry.

References

Glorot, Xavier, Antoine Bordes, and Yoshua Bengio (2011). "Deep Sparse Rectifier Neural Networks". In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS-11). Ed. by Geoffrey J. Gordon and David B. Dunson. Vol. 15. Journal of Machine Learning Research - Workshop and Conference Proceedings, pp. 315-323. URL : http://www.jmlr.org/proceedings/papers/v15/glorot11a/glorot11a.pdf

See Also

Other darch unit functions: exponentialLinearUnit, linearUnit, maxoutUnit, sigmoidUnit, softmaxUnit, softplusUnit, tanhUnit

Examples

## Not run: 
data(iris)
model <- darch(Species ~ ., iris, darch.unitFunction = "rectifiedLinearUnit")

## End(Not run)

darch documentation built on May 29, 2017, 8:14 p.m.