ruby_brain 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 243add4b6f64c99d4bc2de70f69ff74f8fe439fd
-  data.tar.gz: 979c86696fd11c0892031495e57e7f3746b8df2f
+  metadata.gz: e1b359c7dfcb72a2c865c0eb3132d795a14e865b
+  data.tar.gz: cf67ab8cb83e45351d9436b739851813e42dcf27
 SHA512:
-  metadata.gz: a4d8118899133f660ebfb9a64dd1cd068bb7501dff0cf371b6a8937a51fb9d9c0949b45f76176e71404dc745aa766fd9d3853ef34b6015f1d9bc33025df00b48
-  data.tar.gz: e0aec12b42540e424555f50e3bd7784d136fd7d831ee01486967198461d2940d63f174cdcb4a6b7583bb0b5ffdd0aae8968879a45d137d03a07c02b725d13e49
+  metadata.gz: d2f45afd551e3695dd6661bf68d769d40705ca7b0195156fbc6aaec61ccb796511a8b143439c2e109c867ef3dfaf485ac403bb48e350c4b0b28d96c98568a11d
+  data.tar.gz: 1490f842fd47da4290fff7158bdb72c987ff946b02a3f3ccf9feace7ef21fdfb2cb55a11b3dc4c798af52aa1836f27303d067f95918dd35d9b2395dac0b017c7

data/README.org

@@ -38,7 +38,7 @@
 
 *** example "AND"
     Now we assume that we train a network to operate as "AND operator"
-    The true table of "AND operator" is as below.
+    The trueth table of "AND operator" is as below.
     In short, when both "in 1" and "in 2" are 1, the "out" should be 1
     and 0 should be output for other input combinations.
     
@@ -49,7 +49,7 @@
     | 1    | 0    | 0   |
     | 1    | 1    | 1   |
 
-    In this situation, you can prepare the dataset lake following Ruby array.
+    In this situation, you can prepare the dataset like following Ruby array.
     #+BEGIN_SRC ruby
       training_input_set = [
         [0, 0],

data/lib/ruby_brain/network.rb

@@ -4,7 +4,14 @@ module RubyBrain
     def_delegators :@weights_set, :overwrite_weights, :get_weights_as_array
 
     attr_accessor :learning_rate
-
+    
+    # Constructor of Network class
+    # 
+    # @example network structure Array(num_units_list)
+    #  [10, 30, 3]       # => 3 inputs, hidden layer 1 with 30 units, 3 outputs
+    #  [15, 50, 60, 10]  # => 15 inputs, hidden layer 1 with 50 units, hidden layer 2 with 60 units, 10 outputs
+    # 
+    # @param num_units_list [Array] Array which describes the network structure
     def initialize(num_units_list)
       @layers = []
       @num_units_list = num_units_list
@@ -20,6 +27,7 @@ module RubyBrain
     #   @weights_set.overwrite_weights(weights_set_source)
     # end
 
+    # Initialize the network. This method creates network actually based on the network structure Array which specified with Constructor.
     def init_network
       @layers = []
       layer = Layer.new
@@ -52,7 +60,9 @@ module RubyBrain
     #   @weights_set.get_weights_as_array
     # end
 
-
+    # Calculate the network output of forward propagation.
+    #
+    # @param inputs [Array] Input dataset.
     def get_forward_outputs(inputs)
       inputs.each_with_index do |input, i|
         @layers.first.nodes[i].value = input
@@ -66,7 +76,10 @@ module RubyBrain
       end
       a_layer_outputs
     end
-
+    
+    # Calculate the networkoutput of backward propagation.
+    #
+    # @param backward_inputs [Array] Input for backpropagation. Usually it is loss values.
     def run_backpropagate(backward_inputs)
       a_layer_outputs = nil
       a_layer_inputs = backward_inputs
@@ -77,6 +90,8 @@ module RubyBrain
       a_layer_outputs
     end
 
+    # Updates weights actually based on the result of backward propagation
+    #
     def update_weights
       @weights_set.each_weights_with_index do |weights, i|
         weights.each_with_index do |wl, j|
@@ -111,7 +126,14 @@ module RubyBrain
     #   end
     #   Math.sqrt(2.0 * accumulated_errors / training_inputs_set.size)
     # end
-
+    
+    # Starts training with training dataset
+    #
+    # @param inputs_set [Array<Array>] Input dataset for training. The structure is 2 dimentional Array. Eatch dimentions correspond to samples and features.
+    # @param outputs_set [Array<Array>] Output dataset for training. The structure is 2 dimentional Array. Eatch dimentions correspond to samples and features.
+    # @param max_training_count [Integer] Max training count.
+    # @param tolerance [Float] The Threshold to stop training. Training is stopped when RMS error reach to this value even if training count is not max_training_count.
+    # @param monitoring_channels [Array<Symbol>] Specify which log should be reported. Now you can select only `:best_params_training`
     def learn(inputs_set, outputs_set, max_training_count=50, tolerance=0.0, monitoring_channels=[])
       raise RubyBrain::Exception::TrainingDataError if inputs_set.size != outputs_set.size
       #      raise "inputs_set and outputs_set has different size!!!!" if inputs_set.size != outputs_set.size
@@ -240,10 +262,16 @@ module RubyBrain
       end
     end
 
+    # Dumps weights of the network into a file whose format is YAML.
+    # 
+    # @param file_name [String] The path to the YAML file in which weights are saved.
     def dump_weights_to_yaml(file_name=nil)
       @weights_set.dump_to_yaml(file_name)
     end
-
+    
+    # Loads weights of the network from existing weights file whose format is YAML.
+    # 
+    # @param yaml_file [String] The path to the YAML file which includes weights.
     def load_weights_from_yaml_file(yaml_file)
       @weights_set.load_from_yaml_file(yaml_file)
     end

data/lib/ruby_brain/version.rb

@@ -1,3 +1,3 @@
 module RubyBrain
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

data/ruby_brain.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
   spec.authors       = ["elgoog"]
   spec.email         = ["elgoog.development@gmail.com"]
   spec.summary       = %q{NeuralNet/DeepLearning implement for Ruby}
-  spec.description   = %q{NeuralNet/DeepLearning implement for Ruby}
+  spec.description   = %q{Neural Net, Deep Learning implement for Ruby}
   spec.homepage      = "https://github.com/elgoog/ruby_brain/"
   spec.license       = "MIT"
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby_brain
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - elgoog
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-07-26 00:00:00.000000000 Z
+date: 2016-07-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -66,7 +66,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: NeuralNet/DeepLearning implement for Ruby
+description: Neural Net, Deep Learning implement for Ruby
 email:
 - elgoog.development@gmail.com
 executables: []