10
13

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

Python vs Ruby 『ゼロから作るDeep Learning』 2章 パーセプトロンによる論理回路

Last updated at Posted at 2017-05-10

概要

書籍『ゼロから作るDeep Learning ―Pythonで学ぶディープラーニングの理論と実装』2章のコードを参考に Python と Ruby でパーセプトロンによる論理回路
(ANDゲート, NANDゲート, ORゲート, XORゲート)を実装する。

計算処理では外部ライブラリを利用する。Python では NumPy を、Ruby では Numo::NArray を使用する。

環境構築が必要な場合はこちらを参照。
→ Python vs Ruby 『ゼロから作るDeep Learning』 1章 sin関数とcos関数のグラフ http://qiita.com/niwasawa/items/6d9aba43f3cdba5ca725

ANDゲート

重みとバイアスは、人力で適切な値を導いたもの。

Python

and_gate.py

import numpy as np

def AND(x1, x2):
  x = np.array([x1, x2])
  w = np.array([0.5, 0.5]) # 重み
  b = -0.7 # バイアス
  tmp = np.sum(w*x) + b
  if tmp <= 0:
    return 0
  else:
    return 1

if __name__ == '__main__':
  for xs in [(0, 0), (1, 0), (0, 1), (1, 1)]:
    y = AND(xs[0], xs[1])
    print(str(xs) + " -> " + str(y))

Ruby

and_gate.rb

require 'numo/narray'

def AND(x1, x2)
  x = Numo::DFloat[x1, x2]
  w = Numo::DFloat[0.5, 0.5] # 重み
  b = -0.7 # バイアス
  tmp = (w*x).sum + b
  if tmp <= 0
    0
  else
    1
  end
end

if __FILE__ == $0
  for xs in [[0, 0], [1, 0], [0, 1], [1, 1]]
    y = AND(xs[0], xs[1])
    puts "#{xs} -> #{y}"
  end
end

実行結果

Python と Ruby の実行結果を比較する。入力が同じ値の場合は、出力も同じ値になっていることがわかる。

$ python and_gate.py
(0, 0) -> 0
(1, 0) -> 0
(0, 1) -> 0
(1, 1) -> 1

$ ruby and_gate.rb
[0, 0] -> 0
[1, 0] -> 0
[0, 1] -> 0
[1, 1] -> 1

NANDゲート

NANDゲートの実装は、重みとバイアスだけがANDゲートと異なる。

Python

nand_gate.py

import numpy as np

def NAND(x1, x2):
  x = np.array([x1, x2])
  w = np.array([-0.5, -0.5])
  b = 0.7
  tmp = np.sum(w*x) + b
  if tmp <= 0:
    return 0
  else:
    return 1

if __name__ == '__main__':
  for xs in [(0, 0), (1, 0), (0, 1), (1, 1)]:
    y = NAND(xs[0], xs[1])
    print(str(xs) + " -> " + str(y))

Ruby

nand_gate.rb

require 'numo/narray'

def NAND(x1, x2)
  x = Numo::DFloat[x1, x2]
  w = Numo::DFloat[-0.5, -0.5]
  b = 0.7
  tmp = (w*x).sum + b
  if tmp <= 0
    0
  else
    1
  end
end

if __FILE__ == $0
  for xs in [[0, 0], [1, 0], [0, 1], [1, 1]]
    y = NAND(xs[0], xs[1])
    puts "#{xs} -> #{y}"
  end
end

実行結果

$ python nand_gate.py
(0, 0) -> 1
(1, 0) -> 1
(0, 1) -> 1
(1, 1) -> 0

$ ruby nand_gate.rb
[0, 0] -> 1
[1, 0] -> 1
[0, 1] -> 1
[1, 1] -> 0

ORゲート

ORゲートの実装も、重みとバイアスの値のみ異なる。

Python

or_gate.py

import numpy as np

def OR(x1, x2):
  x = np.array([x1, x2])
  w = np.array([0.5, 0.5])
  b = -0.2
  tmp = np.sum(w*x) + b
  if tmp <= 0:
    return 0
  else:
    return 1

if __name__ == '__main__':
  for xs in [(0, 0), (1, 0), (0, 1), (1, 1)]:
    y = OR(xs[0], xs[1])
    print(str(xs) + " -> " + str(y))

Ruby

or_gate.rb

require 'numo/narray'

def OR(x1, x2)
  x = Numo::DFloat[x1, x2]
  w = Numo::DFloat[0.5, 0.5]
  b = -0.2
  tmp = (w*x).sum + b
  if tmp <= 0
    0
  else
    1
  end
end

if __FILE__ == $0
  for xs in [[0, 0], [1, 0], [0, 1], [1, 1]]
    y = OR(xs[0], xs[1])
    puts "#{xs} -> #{y}"
  end
end

実行結果

$ python or_gate.py
(0, 0) -> 0
(1, 0) -> 1
(0, 1) -> 1
(1, 1) -> 1

$ ruby or_gate.rb
[0, 0] -> 0
[1, 0] -> 1
[0, 1] -> 1
[1, 1] -> 1

XORゲート

XORゲートの実装では、NAND・OR・ANDのゲートを重ねた多層パーセプトロンを使う。

Python

xor_gate.py

from and_gate  import AND
from or_gate   import OR
from nand_gate import NAND

def XOR(x1, x2):
  s1 = NAND(x1, x2)
  s2 = OR(x1, x2)
  y  = AND(s1, s2)
  return y

if __name__ == '__main__':
  for xs in [(0, 0), (1, 0), (0, 1), (1, 1)]:
    y = XOR(xs[0], xs[1])
    print(str(xs) + " -> " + str(y))

Ruby

xor_gate.rb

require './and_gate'
require './or_gate'
require './nand_gate'

def XOR(x1, x2)
  s1 = NAND(x1, x2)
  s2 = OR(x1, x2)
  y  = AND(s1, s2)
  return y
end

if __FILE__ == $0
  for xs in [[0, 0], [1, 0], [0, 1], [1, 1]]
    y = XOR(xs[0], xs[1])
    puts "#{xs} -> #{y}"
  end
end

実行結果

$ python xor_gate.py
(0, 0) -> 0
(1, 0) -> 1
(0, 1) -> 1
(1, 1) -> 0

$ ruby xor_gate.rb
[0, 0] -> 0
[1, 0] -> 1
[0, 1] -> 1
[1, 1] -> 0

参考資料

10
13
4

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
10
13

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?