Class: MachineLearningWorkbench::NeuralNetwork::Base

Inherits:
Object
  • Object
show all
Defined in:
lib/machine_learning_workbench/neural_network/base.rb

Overview

Neural Network base class

Direct Known Subclasses

FeedForward, Recurrent

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(struct, act_fn: nil) ⇒ Base

Returns a new instance of Base.

Parameters:

  • struct (Array<Integer>) —

    list of layer sizes

  • act_fn (Symbol) (defaults to: nil) —

    choice of activation function for the neurons



29
30
31
32
33
34
35
36
37
38
39
40
41
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 29

def initialize struct, act_fn: nil
  @struct = struct
  @act_fn_name = act_fn || :sigmoid
  @act_fn = send(act_fn_name)
  # @state holds both inputs, possibly recurrency, and bias
  # it is a complete input for the next layer, hence size from layer sizes
  @state = layer_row_sizes.collect do |size|
    NArray.zeros [1, size]
  end
  # to this, append a matrix to hold the final network output
  @state.push NArray.zeros [1, nneurs(-1)]
  reset_state
end

Instance Attribute Details

#act_fn ⇒ #call (readonly)

activation function, common to all neurons (for now)

Returns:

  • (#call) —

    activation function



22
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 22

attr_reader :layers, :state, :act_fn, :act_fn_name, :struct

#act_fn_name ⇒ Object (readonly)

Returns the value of attribute act_fn_name.



22
23
24
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 22

def act_fn_name
  @act_fn_name
end

#layers ⇒ Array<NArray> (readonly)

List of matrices, each being the weights connecting a layer’s inputs (rows) to a layer’s neurons (columns), hence its shape is ‘[ninputs, nneurs]` TODO: return a NArray after the usage of `#map` is figured out

Returns:

  • (Array<NArray>) —

    list of weight matrices, each uniquely describing a layer



22
23
24
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 22

def layers
  @layers
end

#state ⇒ Array<NArray> (readonly)

It’s a list of one-dimensional matrices, each an input to a layer, plus the output layer’s output. The first element is the input to the first layer of the network, which is composed of the network’s input, possibly the first layer’s activation on the last input (recursion), and a bias (fixed ‘1`). The second to but-last entries follow the same structure, but with the previous layer’s output in place of the network’s input. The last entry is the activation of the output layer, without additions since it’s not used as an input by anyone. TODO: return a NArray after the usage of ‘#map` is figured out

Returns:

  • (Array<NArray>) —

    current state of the network.



22
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 22

attr_reader :layers, :state, :act_fn, :act_fn_name, :struct

#struct ⇒ Object (readonly)

Returns the value of attribute struct.



22
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 22

attr_reader :layers, :state, :act_fn, :act_fn_name, :struct

Instance Method Details

#activate(input) ⇒ Array

Activate the network on a given input

Parameters:

  • input (Array<Float>) —

    the given input

Returns:

  • (Array) —

    the activation of the output layer

Raises:

  • (ArgumentError) 


146
147
148
149
150
151
152
153
154
155
156
157
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 146

def activate input
  raise ArgumentError unless input.size == struct.first
  raise ArgumentError unless input.is_a? Array
  # load input in first state
  @state[0][0, 0..-2] = input
  # activate layers in sequence
  nlayers.times.each do |i|
    act = activate_layer i
    @state[i+1][0, 0...act.size] = act
  end
  return out
end

#deep_reset ⇒ Object

Resets memoization: needed to play with structure modification



62
63
64
65
66
67
68
69
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 62

def deep_reset
  # reset memoization
  [:@layer_row_sizes, :@layer_col_sizes, :@nlayers, :@layer_shapes,
   :@nweights_per_layer, :@nweights].each do |sym|
     instance_variable_set sym, nil
  end
  reset_state
end

#init_random ⇒ Object

Initialize the network with random weights



53
54
55
56
57
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 53

def init_random
  # Will only be used for testing, no sense optimizing it now (NArray#rand)
  # Reusing `#load_weights` instead helps catching bugs
  load_weights nweights.times.collect { rand(-1.0..1.0) }
end

#interface_methods ⇒ Object

Declaring interface methods - implement in child class!



199
200
201
202
203
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 199

[:layer_row_sizes, :activate_layer].each do |sym|
  define_method sym do
    raise NotImplementedError, "Implement ##{sym} in child class!"
  end
end

#layer_col_sizes ⇒ Array

Number of neurons per layer. Although this implementation includes inputs in the layer counts, this methods correctly ignores the input as not having neurons.

Returns:

  • (Array) —

    list of neurons per each (proper) layer (i.e. no inputs)



101
102
103
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 101

def layer_col_sizes
  @layer_col_sizes ||= struct.drop(1)
end

#layer_shapes ⇒ Array<Array[Integer, Integer]>

Shapes for the weight matrices, each corresponding to a layer

Returns:

  • (Array<Array[Integer, Integer]>) —

    Weight matrix shapes



109
110
111
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 109

def layer_shapes
  @layer_shapes ||= layer_row_sizes.zip layer_col_sizes
end

#lecun_hyperbolic ⇒ Object

LeCun hyperbolic activation

See Also:



187
188
189
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 187

def lecun_hyperbolic
  lambda { |x| 1.7159 * Numo::NMath.tanh(2.0*x/3.0) + 1e-3*x }
end

#load_weights(weights) ⇒ true

Loads a plain list of weights into the weight matrices (one per layer). Preserves order. Reuses allocated memory if available.

Returns:

  • (true) —

    always true. If something’s wrong it simply fails, and if all goes well there’s nothing to return but a confirmation to the caller.

Raises:

  • (ArgumentError) 


127
128
129
130
131
132
133
134
135
136
137
138
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 127

def load_weights weights
  raise ArgumentError unless weights.size == nweights
  weights_iter = weights.each
  @layers ||= layer_shapes.collect { |shape| NArray.zeros shape }
  layers.each do |narr|
    narr.each_with_index do |_val, *idxs|
      narr[*idxs] = weights_iter.next
    end
  end
  reset_state
  return true
end

#logistic ⇒ Object

Traditional logistic



177
178
179
180
181
182
183
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 177

def logistic
  lambda { |x|
    exp = Numo::NMath.exp(x)
    # exp.infinite? ? exp : exp / (1.0 + exp)
    exp / (1.0 + exp)
  }
end

#nlayers ⇒ Integer

Count the layers. This is a computation helper, and for this implementation the inputs are considered as if a layer like the others.

Returns:

  • (Integer) —

    number of layers



86
87
88
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 86

def nlayers
  @nlayers ||= layer_shapes.size
end

#nneurs(nlay = nil) ⇒ Integer

Count the neurons in a particular layer or in the whole network.

Parameters:

  • nlay (Integer, nil) (defaults to: nil) —

    the layer of interest, 1-indexed. ‘0` will return the number of inputs. `nil` will compute the total neurons in the network.

Returns:

  • (Integer) —

    the number of neurons in a given layer, or in all network, or the number of inputs



118
119
120
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 118

def nneurs nlay=nil
  nlay.nil? ? struct.reduce(:+) : struct[nlay]
end

#nweights ⇒ Integer

Total weights in the network

Returns:

  • (Integer) —

    total number of weights



73
74
75
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 73

def nweights
  @nweights ||= nweights_per_layer.reduce(:+)
end

#nweights_per_layer ⇒ Array<Integer>

List of per-layer number of weights

Returns:

  • (Array<Integer>) —

    list of weights per each layer



79
80
81
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 79

def nweights_per_layer
  @nweights_per_layer ||= layer_shapes.collect { |shape| shape.reduce(:*) }
end

#out ⇒ Array

Extract and convert the output layer’s activation

Returns:

  • (Array) —

    the activation of the output layer as 1-dim Array



161
162
163
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 161

def out
  state.last.to_a.flatten
end

#relu ⇒ Object

Rectified Linear Unit (ReLU)



192
193
194
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 192

def relu
  lambda { |x| (x>0).all? && x || x.class.zeros(x.shape) }
end

#reset_state ⇒ Object

Reset the network to the initial state



44
45
46
47
48
49
50
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 44

def reset_state
  state.each do |s|
    s.fill 0           # reset state to zero
    s[0,-1] = 1        # add bias
  end
  state[-1][0,-1] = 0  # last layer has no bias
end

#sigmoid(k = 0.5) ⇒ Object

Traditional sigmoid with variable steepness



170
171
172
173
174
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 170

def sigmoid k=0.5
  # k is steepness:  0<k<1 is flatter, 1<k is flatter
  # flatter makes activation less sensitive, better with large number of inputs
  lambda { |x| 1.0 / (Numo::NMath.exp(-k * x) + 1.0) }
end

#weights ⇒ Array

Returns the weight matrix

Returns:

  • (Array) —

    three-dimensional Array of weights: a list of weight matrices, one for each layer.



93
94
95
 
# File 'lib/machine_learning_workbench/neural_network/base.rb', line 93

def weights
  layers.collect(&:to_a)
end