「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」を参考にpythonで制作した簡単な順方向ニューラルネットワークです。 重みはKerasを用いてXORを学習したものを使っています。
Last active
October 27, 2017 01:20
-
-
Save 5hyn3/2cb73b26e94702a6208bb46602a51a0f to your computer and use it in GitHub Desktop.
Python Simple Feed Forward NeuralNetwork
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
def sigmoid(x): | |
return 1 / (1 + np.exp(-x)) | |
def init_network(): | |
network = {} | |
network['W1'] = np.array([[-3.7, -3.9, -1.8], [-3.8, -3.4, -1.8]]) | |
network['W2'] = np.array([[-3.0], [-2.5], [2.9]]) | |
network['b1'] = np.array([-0.4, -0.6, 1.9]) | |
network['b2'] = np.array([-0.4]) | |
return network | |
def forward(network, x): | |
W1, W2 = network['W1'], network['W2'] | |
b1, b2 = network['b1'], network['b2'] | |
a1 = np.dot(x, W1) + b1 | |
z1 = sigmoid(a1) | |
a2 = np.dot(z1, W2) + b2 | |
y = a2 | |
return y | |
network = init_network() | |
x = np.array([0, 1]) | |
y = forward(network, x) | |
print(y) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment