The sigmoid() function returns the sigmoid value of the input(s), by default this is done using the standard logistic function.
## [1] 0.9525741Inputs can also be tensors, such as vectors, matrices, or arrays.
## [1] 0.006692851 0.017986210 0.047425873 0.119202922 0.268941421
## [6] 0.500000000 0.731058579 0.880797078 0.952574127 0.982013790
## [11] 0.993307149## [,1] [,2] [,3]
## [1,] 0.04742587 0.5000000 0.9525741
## [2,] 0.11920292 0.7310586 0.9820138
## [3,] 0.26894142 0.8807971 0.9933071The sigmoid() function is a wrapper, which by default uses the logistic() function, it can also use other methods.
## [1] 3.507389e-65 1.942338e-24 1.892179e-09 6.179790e-04 6.598804e-02
## [6] 3.678794e-01 6.922006e-01 8.734230e-01 9.514320e-01 9.818511e-01
## [11] 9.932847e-01These functions can also be accessed directly.
## [1] 6.598804e-02 6.179790e-04 1.892179e-09 1.942338e-24 3.507389e-65Rectified Linear Unit (ReLU)
## [1] 0 0 0 0 0 0 1 2 3 4 5Leaky Rectified Linear Unit
## [1] -0.05 -0.04 -0.03 -0.02 -0.01 0.00 1.00 2.00 3.00 4.00 5.00These mappings are similar but not identical.
library(ggplot2)
input = -5:5
df = data.frame(input, logistic(input), Gompertz(input))
ggplot(df, aes(input, logistic(input))) + geom_line() +
geom_line(aes(input,Gompertz(input)), colour='red')
The wrapper can also apply the inverse of the method, returning the original values.
## [1] -5 -4 -3 -2 -1 0 1 2 3 4 5Which also works for other methods.
## [1] -5 -4 -3 -2 -1 0 1 2 3 4 5In addition to this, the SoftMax algorithm can be pre applied.
## [1] 0.04742587 0.11920292 0.26894142 0.50000000 0.73105858 0.88079708
## [7] 0.95257413 0.98201379 0.99330715
## [1] 0.01006486 0.03102509 0.09159656 0.24101050 0.50000000 0.75898950
## [7] 0.90840344 0.96897491 0.98993514Several parameters can be specified (for details see help(logistic), etc.). This can for instance be used to preserve greater entropy.
