newral 0.1 → 0.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 281bfa9ba74cbd19d659513e73eae475f6f1ec7e
-  data.tar.gz: 99a0085f6bc6a1b6a38237dc330110950df04f19
+  metadata.gz: b9047684d474438632d4eab4774fbb7b9debecc5
+  data.tar.gz: 0d83a2232560366d75af79b848fbbb8ba358169d
 SHA512:
-  metadata.gz: 63af6de490824297c3561b6e1c77f1681d099e17e38323fbd15080b4447a08abe8fd83c257a8e1c2936e08591260798895cf526af2288dda188ad12490b3e19d
-  data.tar.gz: 786ff86c34e25ad4bbbb4cfd322c0d40efa39308778ab18efd6641bb3126e62e3ad6af02ecc608bc2225fcbb66519d15645e8a603d744e7feb9110d61a8401f1
+  metadata.gz: 27e1bca6445adcc1d518d898e2e0e027d0d573eaba8bae588a9350a6d676d285afa549a9bc2a1ac07019f44645dc6cf8516b389069f50bf03ff8c3b322a0b0ea
+  data.tar.gz: 505f5faa6a843b4b5ab9e2c6654f6a8c32aa692bcf73d5058f95b3167a30c649979f250bbb17720d119e06a4aae5a4224a6d40ee53931607ca5caca3a061f9ed

data/README.md

@@ -9,7 +9,13 @@ In the implementation I tried to write as little code as possible and used class
 So the data structures are in no way tuned for efficiency, rather I tried to make clear what actually is going on.
 For every concept there should be at least one test to show it in action.
 
+## Install
 
+```ruby
+gem install newral
+```
+
+## What it does
 Everything is still quite early stages but there are a lot of things you can do already
 
 * Training Functions 
@@ -167,13 +173,13 @@ data = Newral::Data::Csv.new(file_name:File.expand_path('../test/fixtures/IRIS.c
 data.process
 
 network = Newral::Networks::BackpropagationNetwork.new( number_of_inputs: data.inputs.first.size, number_of_hidden: data.inputs.first.size, number_of_outputs: data.output_hash.keys.size )
-network.calculate_error( input: data.sub_set(set: :inputs, category: :validation ), output: data.output_as_vector( category: :testing ) ) 
+network.calculate_error( input: data.sub_set(set: :inputs, category: :validation ), output: data.output_as_vector( category: :validation ) ) 
 
 100.times do
   network.train( input: data.sub_set(set: :inputs, category: :training ), output: data.output_as_vector( category: :training ) ) 
 end 
 
-network.calculate_error( input: data.sub_set(set: :inputs, category: :validation ), output: data.output_as_vector( category: :testing ) ) 
+network.calculate_error( input: data.sub_set(set: :inputs, category: :validation ), output: data.output_as_vector( category: :validation ) ) 
 
 ```
 
@@ -186,7 +192,7 @@ data.process
 sample_data = data.sample( limit:100 ) 
 sample_data.downsample_input!( width:2,height:2,width_of_line:28 ) # create less resolution pictures
 
-sample_data2 = data.sample( limit:100, offset:100  ) # a 2bd sample
+sample_data2 = data.sample( limit:100, offset:100  ) # a 2nd sample
 sample_data2.downsample_input!( width:2,height:2,width_of_line:28 )
 
 
@@ -252,7 +258,7 @@ f.calculate 2 # 2*(2**2)+5*2+1 => 19
 first lets use a basic polynominal function 
 ```ruby
       input = [2,4,8]
-      output = [4,16,64] # best function is x**2, lets see if our training algorithms find them
+      output = [4,16,64] # best function is x**2, lets see if our training algorithms finds them
       g=Newral::Training::Greedy.new( input: input, output: output, klass: Newral::Functions::Polynomial )
       g.process 
       g.best_function.calculate_error( input: input, output: output )

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: newral
 version: !ruby/object:Gem::Version
-  version: '0.1'
+  version: '0.11'
 platform: ruby
 authors:
 - stefan