brains 0.1.1-java → 0.2.0-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 555149c0570a03a1ef8af988f8114013457cc2ca
-  data.tar.gz: 01fb0792ebd5b148ea5ab0da4f43cf5da4d482a4
+  metadata.gz: 1b6deee0363d18d2c2d4a7ea8b4047681776566a
+  data.tar.gz: 88dd27bf0f07c4895f0871e80dba2f7909ab02bd
 SHA512:
-  metadata.gz: 96f733e7575451619ae2c354921059cb4c2b06524d69d14433b0aeb3b202054caf79cf6ea42153e69e14d16a8c3e551de004629b4189d24e648e39a92c49807f
-  data.tar.gz: ee83b4c978701cfd4095cd0d8de754e8e371fe0e543648d8f1cb4c625c265cd52d9ab3de4b3a14212f5b3f27ea0bfc6d15b530ce10a55d0b1651c37f43a4de39
+  metadata.gz: 0cef015a95f1237f286606cbb439e8370920e3fc6bd9eebf2f68d03471c20383cb930495740a34dc51d5543e6560c3f739ccb61ceabeb1eed1e3d649fd60a64d
+  data.tar.gz: 690b8de89fd2dfe1f98f9bbe9594c5af7bf28b1abb2940589433a0e304d7dd3e95dbc2420b3c68768f8a4f1fd5e72d35d1bb266e9a838edf0d4aa309a138036a

data/CHANGELOG.md

@@ -0,0 +1,4 @@
+Version 0.2.0
+-------------
+
+* Support for multilayer recurrent neural networks

data/README.md

@@ -154,12 +154,24 @@ https://github.com/jedld/brains
 
 You can compile the java source code as brains.jar and use it directly with this gem.
 
+## RNNs (Recurrent Neural Networks)
+
+For recurrent neural networks (Look at the sine function in the examples). Only
+the backpropagation through time (BPTT) training algorithm is
+supported for now.
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
 To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
 
+## Resources
+
+Machine learning is still a rapidly evolving field and research is ongoing on various aspects of it. This is just the tip of the iceberg, the field of machine learning is extremely complex, below are various resources for the average developer to get started:
+
+ftp://ftp.sas.com/pub/neural/FAQ.html#questions
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/brains. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.

data/brains.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
   spec.email         = ["joseph.dayo@gmail.com"]
 
   spec.summary       = %q{A feedforward neural network library for JRuby}
-  spec.description   = %q{A feedforward neural network library for JRuby}
+  spec.description   = %q{A feedforward neural network library for JRuby. Aims to provide a quick way to get started on machine learning with ruby }
   spec.homepage      = "https://github.com/jedld/brains-jruby"
   spec.license       = "MIT"
   spec.platform      = "java"

data/example/colors.rb

@@ -3,43 +3,95 @@
 require 'brains'
 
 #This neural network will identify the main color name based on rgb values
+RED = [0,0,1]
+GREEN = [0,1,0]
+BLUE = [1,0,0]
+
+def color_value(color_value)
+   [
+     Integer(color_value[0..1], 16).to_f / 0xff.to_f,
+     Integer(color_value[2..3], 16).to_f / 0xff.to_f,
+     Integer(color_value[4..5], 16).to_f / 0xff.to_f,
+   ]
+end
+
+def color_desc(result)
+  return "blue" if (result[0] > result[1] && result[0] > result[2])
+  return "green" if (result[1] > result[0] && result[1] > result[2])
+  return "red" if (result[2] > result[0] && result[2] > result[1])
+end
 
 label_encodings = {
-  "Red"   => [1, 0, 0],
+  "Blue"   => [1, 0, 0],
   "Green" => [0, 1, 0],
-  "Blue"  => [0, 0 ,1]
+  "Red"  => [0, 0 ,1]
 }
 #0000ff
 training_data = [
-  [[0xf0/0xff.to_f, 0xf8.to_f/0xff.to_f, 1],[0,0,1]],
-  [[0x00/0xff.to_f, 0x00.to_f/0xff.to_f, 1],[0,0,1]],
-  [[0x00/0xff.to_f, 0x00.to_f/0xff.to_f, 0x8b.to_f/0xff.to_f],[0,0,1]]
+  # red
+  [color_value('E32636'), RED],
+  [color_value('8B0000'), RED],
+  [color_value('800000'), RED],
+  [color_value('65000B'), RED],
+  [color_value('674846'), RED],
+
+  #green
+  [color_value('8F9779'), GREEN],
+  [color_value('568203'), GREEN],
+  [color_value('013220'), GREEN],
+  [color_value('00FF00'), GREEN],
+  [color_value('006400'), GREEN],
+  [color_value('00A877'), GREEN],
+
+  #blue
+  [color_value('89CFF0'), BLUE],
+  [color_value('ADD8E6'), BLUE],
+  [color_value('0000FF'), BLUE],
+  [color_value('0070BB'), BLUE],
+  [color_value('545AA7'), BLUE],
+  [color_value('4C516D'), BLUE],
 ]
 
-nn = Brains::Net.create(2, 1, 9, { neurons_per_layer: 4 })
+nn = Brains::Net.create(3, 3, 2, { neurons_per_layer: 5 })
+
+# randomize weights before training
 nn.randomize_weights
 
 
 # test on untrained data
-#0000ee
+#0000ee 	#C41E3A
 test_data = [
-  [0x00/0xff.to_f, 0x00.to_f/0xff.to_f, 0xee.to_f/0xff.to_f],
+  [color_value('0087BD') , 'blue'], # blue
+  [color_value('C80815') , 'red'], # venetian red
+  [color_value('009E60') , 'green'], # Shamrock green
+  [color_value('00FF00') , 'green'], # green
+  [color_value('333399') , 'blue'], # blue
 ]
 
-results = test_data.collect { |item|
-  nn.feed(item)
+correct = 0
+test_data.each_with_index { |item , index|
+  c = color_desc(nn.feed(item[0]))
+  correct +=1 if (c == item[1])
+  puts c
 }
 
-p results
+puts "#{correct}/#{test_data.length}"
 
-result = nn.optimize(training_data, 0.01, 1_000 ) { |i, error|
+result = nn.optimize(training_data, 0.005, 1_000_000, 100 ) { |i, error|
   puts "#{i} #{error}"
 }
 
+p result
+
 puts "after training"
 
-results = test_data.collect { |item|
-  nn.feed(item)
+correct = 0
+test_data.each_with_index { |item , index|
+  c = color_desc(nn.feed(item[0]))
+  correct +=1 if (c == item[1])
+  puts c
 }
 
-p results
+puts "#{correct}/#{test_data.length}"
+
+puts nn.to_json

data/example/iris.data

@@ -0,0 +1,150 @@
+5.1,3.5,1.4,0.2,Iris-setosa
+4.9,3.0,1.4,0.2,Iris-setosa
+4.7,3.2,1.3,0.2,Iris-setosa
+4.6,3.1,1.5,0.2,Iris-setosa
+5.0,3.6,1.4,0.2,Iris-setosa
+5.4,3.9,1.7,0.4,Iris-setosa
+4.6,3.4,1.4,0.3,Iris-setosa
+5.0,3.4,1.5,0.2,Iris-setosa
+4.4,2.9,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.4,3.7,1.5,0.2,Iris-setosa
+4.8,3.4,1.6,0.2,Iris-setosa
+4.8,3.0,1.4,0.1,Iris-setosa
+4.3,3.0,1.1,0.1,Iris-setosa
+5.8,4.0,1.2,0.2,Iris-setosa
+5.7,4.4,1.5,0.4,Iris-setosa
+5.4,3.9,1.3,0.4,Iris-setosa
+5.1,3.5,1.4,0.3,Iris-setosa
+5.7,3.8,1.7,0.3,Iris-setosa
+5.1,3.8,1.5,0.3,Iris-setosa
+5.4,3.4,1.7,0.2,Iris-setosa
+5.1,3.7,1.5,0.4,Iris-setosa
+4.6,3.6,1.0,0.2,Iris-setosa
+5.1,3.3,1.7,0.5,Iris-setosa
+4.8,3.4,1.9,0.2,Iris-setosa
+5.0,3.0,1.6,0.2,Iris-setosa
+5.0,3.4,1.6,0.4,Iris-setosa
+5.2,3.5,1.5,0.2,Iris-setosa
+5.2,3.4,1.4,0.2,Iris-setosa
+4.7,3.2,1.6,0.2,Iris-setosa
+4.8,3.1,1.6,0.2,Iris-setosa
+5.4,3.4,1.5,0.4,Iris-setosa
+5.2,4.1,1.5,0.1,Iris-setosa
+5.5,4.2,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.0,3.2,1.2,0.2,Iris-setosa
+5.5,3.5,1.3,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+4.4,3.0,1.3,0.2,Iris-setosa
+5.1,3.4,1.5,0.2,Iris-setosa
+5.0,3.5,1.3,0.3,Iris-setosa
+4.5,2.3,1.3,0.3,Iris-setosa
+4.4,3.2,1.3,0.2,Iris-setosa
+5.0,3.5,1.6,0.6,Iris-setosa
+5.1,3.8,1.9,0.4,Iris-setosa
+4.8,3.0,1.4,0.3,Iris-setosa
+5.1,3.8,1.6,0.2,Iris-setosa
+4.6,3.2,1.4,0.2,Iris-setosa
+5.3,3.7,1.5,0.2,Iris-setosa
+5.0,3.3,1.4,0.2,Iris-setosa
+7.0,3.2,4.7,1.4,Iris-versicolor
+6.4,3.2,4.5,1.5,Iris-versicolor
+6.9,3.1,4.9,1.5,Iris-versicolor
+5.5,2.3,4.0,1.3,Iris-versicolor
+6.5,2.8,4.6,1.5,Iris-versicolor
+5.7,2.8,4.5,1.3,Iris-versicolor
+6.3,3.3,4.7,1.6,Iris-versicolor
+4.9,2.4,3.3,1.0,Iris-versicolor
+6.6,2.9,4.6,1.3,Iris-versicolor
+5.2,2.7,3.9,1.4,Iris-versicolor
+5.0,2.0,3.5,1.0,Iris-versicolor
+5.9,3.0,4.2,1.5,Iris-versicolor
+6.0,2.2,4.0,1.0,Iris-versicolor
+6.1,2.9,4.7,1.4,Iris-versicolor
+5.6,2.9,3.6,1.3,Iris-versicolor
+6.7,3.1,4.4,1.4,Iris-versicolor
+5.6,3.0,4.5,1.5,Iris-versicolor
+5.8,2.7,4.1,1.0,Iris-versicolor
+6.2,2.2,4.5,1.5,Iris-versicolor
+5.6,2.5,3.9,1.1,Iris-versicolor
+5.9,3.2,4.8,1.8,Iris-versicolor
+6.1,2.8,4.0,1.3,Iris-versicolor
+6.3,2.5,4.9,1.5,Iris-versicolor
+6.1,2.8,4.7,1.2,Iris-versicolor
+6.4,2.9,4.3,1.3,Iris-versicolor
+6.6,3.0,4.4,1.4,Iris-versicolor
+6.8,2.8,4.8,1.4,Iris-versicolor
+6.7,3.0,5.0,1.7,Iris-versicolor
+6.0,2.9,4.5,1.5,Iris-versicolor
+5.7,2.6,3.5,1.0,Iris-versicolor
+5.5,2.4,3.8,1.1,Iris-versicolor
+5.5,2.4,3.7,1.0,Iris-versicolor
+5.8,2.7,3.9,1.2,Iris-versicolor
+6.0,2.7,5.1,1.6,Iris-versicolor
+5.4,3.0,4.5,1.5,Iris-versicolor
+6.0,3.4,4.5,1.6,Iris-versicolor
+6.7,3.1,4.7,1.5,Iris-versicolor
+6.3,2.3,4.4,1.3,Iris-versicolor
+5.6,3.0,4.1,1.3,Iris-versicolor
+5.5,2.5,4.0,1.3,Iris-versicolor
+5.5,2.6,4.4,1.2,Iris-versicolor
+6.1,3.0,4.6,1.4,Iris-versicolor
+5.8,2.6,4.0,1.2,Iris-versicolor
+5.0,2.3,3.3,1.0,Iris-versicolor
+5.6,2.7,4.2,1.3,Iris-versicolor
+5.7,3.0,4.2,1.2,Iris-versicolor
+5.7,2.9,4.2,1.3,Iris-versicolor
+6.2,2.9,4.3,1.3,Iris-versicolor
+5.1,2.5,3.0,1.1,Iris-versicolor
+5.7,2.8,4.1,1.3,Iris-versicolor
+6.3,3.3,6.0,2.5,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+7.1,3.0,5.9,2.1,Iris-virginica
+6.3,2.9,5.6,1.8,Iris-virginica
+6.5,3.0,5.8,2.2,Iris-virginica
+7.6,3.0,6.6,2.1,Iris-virginica
+4.9,2.5,4.5,1.7,Iris-virginica
+7.3,2.9,6.3,1.8,Iris-virginica
+6.7,2.5,5.8,1.8,Iris-virginica
+7.2,3.6,6.1,2.5,Iris-virginica
+6.5,3.2,5.1,2.0,Iris-virginica
+6.4,2.7,5.3,1.9,Iris-virginica
+6.8,3.0,5.5,2.1,Iris-virginica
+5.7,2.5,5.0,2.0,Iris-virginica
+5.8,2.8,5.1,2.4,Iris-virginica
+6.4,3.2,5.3,2.3,Iris-virginica
+6.5,3.0,5.5,1.8,Iris-virginica
+7.7,3.8,6.7,2.2,Iris-virginica
+7.7,2.6,6.9,2.3,Iris-virginica
+6.0,2.2,5.0,1.5,Iris-virginica
+6.9,3.2,5.7,2.3,Iris-virginica
+5.6,2.8,4.9,2.0,Iris-virginica
+7.7,2.8,6.7,2.0,Iris-virginica
+6.3,2.7,4.9,1.8,Iris-virginica
+6.7,3.3,5.7,2.1,Iris-virginica
+7.2,3.2,6.0,1.8,Iris-virginica
+6.2,2.8,4.8,1.8,Iris-virginica
+6.1,3.0,4.9,1.8,Iris-virginica
+6.4,2.8,5.6,2.1,Iris-virginica
+7.2,3.0,5.8,1.6,Iris-virginica
+7.4,2.8,6.1,1.9,Iris-virginica
+7.9,3.8,6.4,2.0,Iris-virginica
+6.4,2.8,5.6,2.2,Iris-virginica
+6.3,2.8,5.1,1.5,Iris-virginica
+6.1,2.6,5.6,1.4,Iris-virginica
+7.7,3.0,6.1,2.3,Iris-virginica
+6.3,3.4,5.6,2.4,Iris-virginica
+6.4,3.1,5.5,1.8,Iris-virginica
+6.0,3.0,4.8,1.8,Iris-virginica
+6.9,3.1,5.4,2.1,Iris-virginica
+6.7,3.1,5.6,2.4,Iris-virginica
+6.9,3.1,5.1,2.3,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+6.8,3.2,5.9,2.3,Iris-virginica
+6.7,3.3,5.7,2.5,Iris-virginica
+6.7,3.0,5.2,2.3,Iris-virginica
+6.3,2.5,5.0,1.9,Iris-virginica
+6.5,3.0,5.2,2.0,Iris-virginica
+6.2,3.4,5.4,2.3,Iris-virginica
+5.9,3.0,5.1,1.8,Iris-virginica

data/example/sine_function.rb

@@ -0,0 +1,53 @@
+#!/usr/bin/env ruby
+
+require 'brains'
+
+# RNN to approximate a sine function sequence
+
+def generate_sine_test_data(start_t, end_t)
+  inputs = []
+  outputs = []
+
+  (start_t...end_t).each do |t|
+    inputs << [Math.sin(t)]
+    outputs << [Math.sin(t + 1)]
+  end
+
+  [[inputs, outputs]]
+end
+
+
+
+training_data = generate_sine_test_data(0, 10)
+
+testing_data = generate_sine_test_data(11, 20)
+
+# input sequence
+input_sequence = training_data[0][0].map { |a| a[0] }
+test_input_sequence = testing_data[0][0].map { |a| a[0] }
+test_output_sequence = testing_data[0][1].map { |a| a[0] }
+
+nn = Brains::Net.create(1, 1, 1, { neurons_per_layer: 3,
+      learning_rate: 0.01,
+      recurrent: true,
+      output_function: :htan,
+     })
+
+# randomize weights before training
+nn.randomize_weights
+
+results = nn.feed(testing_data[0][0])
+results.each_with_index do |a, index|
+  puts "#{test_input_sequence[index]} => #{a[0]}"
+end
+
+result = nn.optimize_recurrent(training_data, 0.001, 100_000, 10_000 ) { |i, error|
+  puts "#{i} #{error}"
+}
+
+results = nn.feed(testing_data[0][0])
+results.each_with_index do |a, index|
+  puts "#{test_input_sequence[index]} => #{a[0]} (#{test_output_sequence[index]})"
+end
+
+puts nn.to_json

data/lib/brains/net.rb

@@ -13,10 +13,11 @@ module Brains
       config.learningRate = opts[:learning_rate] || 0.1
       config.neuronsPerLayer = neurons_per_layer
       config.momentumFactor = opts[:momentum_factor] || 0.5
+      config.isRecurrent = opts[:recurrent] || false
       config.backPropagationAlgorithm = opt_t_back_alg(opts[:train_method] || :standard)
       config.activationFunctionType = opt_to_func(opts[:activation_function] || :htan)
-      config.outputActivationFunctionType = opt_to_func(opts[:activation_function] || :sigmoid)
-      config.errorFormula = opt_to_error_func(opts[:activation_function] || :mean_squared)
+      config.outputActivationFunctionType = opt_to_func(opts[:output_function] || :sigmoid)
+      config.errorFormula = opt_to_error_func(opts[:error] || :mean_squared)
       nn = com.dayosoft.nn.NeuralNet.new(config);
 
       Brains::Net.new.set_nn(nn).set_config(config)
@@ -55,8 +56,68 @@ module Brains
       { iterations: result.first, error: result.second }
     end
 
+    def optimize_recurrent(test_cases, target_error = 0.01, max_epoch = 1_000_000_000,
+        callback_interval = 1000, max_layers = 0, &callback)
+      inputs = []
+      outputs = []
+
+      input_set = java.util.ArrayList.new
+      output_set = java.util.ArrayList.new
+
+      test_cases.each do |item|
+
+        inputs = java.util.ArrayList.new
+        outputs = java.util.ArrayList.new
+
+        item[0].each do |item|
+          inputs.add(item.to_java(Java::double))
+        end
+
+        item[1].each do |item|
+          outputs.add(item.to_java(Java::double))
+        end
+
+        input_set.add(inputs)
+        output_set.add(outputs)
+      end
+
+      result = @nn.optimizeRecurrent(input_set, output_set, target_error, max_layers, max_epoch,
+        callback_interval, callback)
+
+      { iterations: result.first, error: result.second }
+    end
+
     def feed(input)
-      output = @nn.feed(input.to_java(Java::double)).to_a
+      # recurrent mode when array of array is passed.
+      if input && input.size > 0 && input[0].kind_of?(Array)
+        feed_recurrent(input)
+      else
+        result = @nn.feed(input.to_java(Java::double)).to_a
+        @nn.updatePreviousOutputs if config.isRecurrent
+
+        result
+      end
+    end
+
+    # For a recurrent network, this resets hidden states back to zero
+    def reset
+      if config.isRecurrent
+        @nn.resetRecurrentStates
+      else
+        puts "Warning not a recurrent network. This does nothing"
+      end
+    end
+
+    def feed_recurrent(inputs)
+      inputset = java.util.ArrayList.new
+      inputs.each do |input|
+        inputset.add(input.to_java(Java::double))
+      end
+
+      output_set = @nn.feed(inputset).to_a
+      output_set.collect do |output|
+        output.to_a
+      end
     end
 
     def to_json
@@ -101,6 +162,8 @@ module Brains
         com.dayosoft.nn.NeuralNet::Config::STANDARD_BACKPROPAGATION
       when :rprop
         com.dayosoft.nn.NeuralNet::Config::RPROP_BACKPROPAGATION
+      else
+        raise "Invalid backpropagation method #{func}"
       end
     end
 

data/lib/brains/version.rb

@@ -1,3 +1,3 @@
 module Brains
-  VERSION = "0.1.1"
+  VERSION = "0.2.0"
 end

metadata

@@ -1,58 +1,59 @@
 --- !ruby/object:Gem::Specification
 name: brains
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
 platform: java
 authors:
 - Joseph Emmanuel Dayo
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2017-02-23 00:00:00.000000000 Z
+date: 2017-03-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: bundler
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.12'
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.12'
+  name: bundler
   prerelease: false
   type: :development
-- !ruby/object:Gem::Dependency
-  name: rake
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '1.12'
+- !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
+  name: rake
   prerelease: false
   type: :development
-- !ruby/object:Gem::Dependency
-  name: rspec
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '10.0'
+- !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
+  name: rspec
   prerelease: false
   type: :development
-description: A feedforward neural network library for JRuby
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: 'A feedforward neural network library for JRuby. Aims to provide a quick
+  way to get started on machine learning with ruby '
 email:
 - joseph.dayo@gmail.com
 executables: []
@@ -62,6 +63,7 @@ files:
 - ".gitignore"
 - ".rspec"
 - ".travis.yml"
+- CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - Gemfile
 - LICENSE.txt
@@ -71,7 +73,9 @@ files:
 - bin/setup
 - brains.gemspec
 - example/colors.rb
+- example/iris.data
 - example/iris.rb
+- example/sine_function.rb
 - example/xor.rb
 - iris.data
 - lib/brains.rb
@@ -102,7 +106,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.4.8
+rubygems_version: 2.6.8
 signing_key:
 specification_version: 4
 summary: A feedforward neural network library for JRuby