Class: Neuronet::LogNormal

Inherits:
Gaussian show all
Defined in:
lib/neuronet/log_normal.rb

Overview

“Log-Normal Distribution” LogNormal sub-classes Gaussian to transform the values to a logarithmic scale.

Instance Attribute Summary

Attributes inherited from Scale

#center, #spread

Instance Method Summary collapse

Methods inherited from Scale

#initialize, #reset

Constructor Details

This class inherits a constructor from Neuronet::Scale

Instance Method Details

#mapped(inputs) ⇒ Object 



13
14
15
 
# File 'lib/neuronet/log_normal.rb', line 13

def mapped(inputs)
  super(inputs.map { |value| Math.log(value) })
end

#set(inputs) ⇒ Object 



9
10
11
 
# File 'lib/neuronet/log_normal.rb', line 9

def set(inputs)
  super(inputs.map { |value| Math.log(value) })
end

#unmapped(outputs) ⇒ Object 



17
18
19
 
# File 'lib/neuronet/log_normal.rb', line 17

def unmapped(outputs)
  super(outputs).map { |value| Math.exp(value) }
end