Class: Neuronet::Scale

Inherits:
Object
  • Object
show all
Defined in:
lib/neuronet.rb

Overview

Scales the problem

Direct Known Subclasses

Gaussian

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(factor = 1.0, center = nil, spread = nil) ⇒ Scale

Returns a new instance of Scale.



230
231
232
233
234
 
# File 'lib/neuronet.rb', line 230

def initialize(factor=1.0,center=nil,spread=nil)
  @factor,@center,@spread = factor,center,spread
  @centered, @spreaded = center.nil?, spread.nil?
  @init = true
end

Instance Attribute Details

#center ⇒ Object

Returns the value of attribute center.



227
228
229
 
# File 'lib/neuronet.rb', line 227

def center
  @center
end

#init=(value) ⇒ Object (writeonly)

Sets the attribute init

Parameters:

  • value —

    the value to set the attribute init to.



228
229
230
 
# File 'lib/neuronet.rb', line 228

def init=(value)
  @init = value
end

#spread ⇒ Object

Returns the value of attribute spread.



227
228
229
 
# File 'lib/neuronet.rb', line 227

def spread
  @spread
end

Instance Method Details

#mapped(inputs) ⇒ Object Also known as: mapped_input, mapped_output 



258
259
260
261
 
# File 'lib/neuronet.rb', line 258

def mapped(inputs)
  factor = 1.0 / (@factor*@spread)
  inputs.map{|value| factor*(value - @center)}
end

#set(inputs) ⇒ Object 



252
253
254
255
256
 
# File 'lib/neuronet.rb', line 252

def set(inputs)
  set_init(inputs)		if @init
  set_center(inputs)	if @centered
  set_spread(inputs)	if @spreaded
end

#set_center(inputs) ⇒ Object

In this case, inputs is unused, but it’s there for the general case.



248
249
250
 
# File 'lib/neuronet.rb', line 248

def set_center(inputs)
  @center = (@max + @min) / 2.0
end

#set_init(inputs) ⇒ Object 



236
237
238
 
# File 'lib/neuronet.rb', line 236

def set_init(inputs)
  @min, @max = inputs.minmax
end

#set_spread(inputs) ⇒ Object

In this case, inputs is unused, but it’s there for the general case.



242
243
244
 
# File 'lib/neuronet.rb', line 242

def set_spread(inputs)
  @spread = (@max - @min) / 2.0
end

#unmapped(outputs) ⇒ Object Also known as: unmapped_input, unmapped_output

Note that it could also unmap inputs, but outputs is typically what’s being transformed back.



267
268
269
270
 
# File 'lib/neuronet.rb', line 267

def unmapped(outputs)
  factor = @factor*@spread
  outputs.map{|value| factor*value + @center}
end