Module: Neuronet::LayerPresets

Included in:
Layer, MiddleLayer, OutputLayer
Defined in:
lib/neuronet/layer_presets.rb

Overview

LayerPresets initializes layer weights/biases for interpret-able functions.

Constant Summary collapse

BZERO = 
0.5 / (0.5 - Squash.squash(1.0))
WONE = 
-2.0 * BZERO

Instance Method Summary collapse

Instance Method Details

#antithesis ⇒ Object

Doubles up the input both mirroring and anti-mirroring it. The layer should be twice the size of the input.



20
21
22
23
24
25
26
27
 
# File 'lib/neuronet/layer_presets.rb', line 20

def antithesis
  sign = 1.0
  each_with_index do |neuron, index|
    neuron.bias = sign * BZERO
    neuron.connections[index / 2].weight = sign * WONE
    sign = -sign
  end
end

#average(sign = 1.0) ⇒ Object

Set layer to average input.



43
44
45
46
47
48
49
50
51
 
# File 'lib/neuronet/layer_presets.rb', line 43

def average(sign = 1.0)
  bias = sign * BZERO
  each do |neuron|
    neuron.bias = bias
    connections = neuron.connections
    weight = sign * WONE / connections.size
    connections.each { it.weight = weight }
  end
end

#mirror(sign = 1.0) ⇒ Object

Set layer to roughly mirror it’s input. Input should be the same size as the layer.



11
12
13
14
15
16
 
# File 'lib/neuronet/layer_presets.rb', line 11

def mirror(sign = 1.0)
  each_with_index do |neuron, index|
    neuron.bias = sign * BZERO
    neuron.connections[index].weight = sign * WONE
  end
end

#synthesis(sign = 1.0) ⇒ Object

Sums two corresponding input neurons above each neuron in the layer. Input should be twice the size of the layer.



31
32
33
34
35
36
37
38
39
40
 
# File 'lib/neuronet/layer_presets.rb', line 31

def synthesis(sign = 1.0)
  semi = sign * WONE / 2.0
  each_with_index do |neuron, index|
    neuron.bias = sign * BZERO
    j = index * 2
    connections = neuron.connections
    connections[j].weight = semi
    connections[j + 1].weight = semi
  end
end