bin.entropy: Binary Entropy

In modello: Homemade Deep Learning Library

Description

Entropy for binary target variables (Negative Bernoulli Log-Likelihood)

h = ∑_i{-y_i * log(\hat y_i) - (1- y_i) * log(1 - \hat y_i)}

Usage

## S3 method for class 'modello_number'
bin.entropy(y, yh)

## Default S3 method:
bin.entropy(y, yh)

bin.entropy(y, yh)

Arguments

y	predicted probability
yh	target classes (0 or 1)

Value

Returns the entropy

Author(s)

Filippo Monari

Examples

modello.init(10, 10, 10, 10)
## For modello_numbers
y = number(sample(c(1, 0), 10, replace=TRUE), dx=FALSE)
yh = number(runif(10))
h = bin.entropy(y, yh)
print(h)
print(h$v)
modello.close()
## For numerics
y = sample(c(1, 0), 10, replace=TRUE)
yh = runif(10)
h = bin.entropy(y, yh)
print(h)

modello documentation built on Feb. 2, 2021, 9:06 a.m.