Module: Neuronet::NeuronStats

Included in:
InputNeuron, MiddleNeuron, Neuron, OutputNeuron
Defined in:
lib/neuronet/neuron_stats.rb

Overview

NeuronStats provides network analysis methods.

Instance Method Summary collapse

Instance Method Details

#downstream_params_tally ⇒ Object

Returns the total tally of parameters in the downstream network subgraph from this neuron. This includes the neuron’s bias (1 parameter), the weights of its incoming connections (one per connection), and the sum of parameters from all downstream neurons. Parameters from a shared neuron are counted multiple times if accessed via multiple pathways, reflecting the total parameter influence through all paths. Returns 0 for a neuron with no downstream connections.



15
16
17
18
19
 
# File 'lib/neuronet/neuron_stats.rb', line 15

def downstream_params_tally
  return 0 if (size = connections.size).zero?

  1 + size + connections.sum { it.neuron.downstream_params_tally }
end

#mju ⇒ Object

Sum of activations + 1. It’s a component of the sensitivity measure nju. See [wiki](github.com/carlosjhr64/neuronet/wiki)



23
 
# File 'lib/neuronet/neuron_stats.rb', line 23

def mju = 1 + connections.sum { it.neuron.activation }

#nju ⇒ Object

Sensitivity measure nju:

See the [wiki](github.com/carlosjhr64/neuronet/wiki) See also test/tc_epsilon:

https://github.com/carlosjhr64/neuronet/blob/master/test/tc_epsilon

rubocop: disable Metrics



33
34
35
36
37
38
39
40
41
42
 
# File 'lib/neuronet/neuron_stats.rb', line 33

def nju
  return 0 if connections.empty?

  mju + connections.sum do |connection|
    n = connection.neuron
    next 0.0 if (nju = n.nju).zero? || (a = n.activation).zero? || a >= 1.0

    connection.weight * a * (1.0 - a) * nju
  end
end