softplusUnit: Softplus 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 softmax activation of the units and the second entry is the derivative of the transfer function. Softplus is a smoothed version of the rectified linear activation function.

Usage

softplusUnit(input, ...)

Arguments

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

Value

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

References

Dugas, Charles, Yoshua Bengio, Francois Belisle, Claude Nadeau, and Rene Garcia (2001). "Incorporating Second-Order Functional Knowledge for Better Option Pricing". In: Advances in Neural Information Processing Systems, pp. 472-478.

See Also

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

Examples

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

## End(Not run)

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