def multilayer_perceptron():
mlnn = MultiLayerNeuralNetwork( [2, 4, 1],
threshold=0.5,
learning_coefficient=0.5,
sigmoid_alpha=5)
x_range = [0,10]
y_range = [0,10]
# liner_data = TrainingData.liner_training_data(x_range, y_range)
#liner_data = TrainingData.quadratic_function_data(x_range, y_range)
liner_data = TrainingData.sin_function_data(x_range, y_range, 5)
train_data = TrainingData.change_format(liner_data)
# 教師データのプロット
fig = plt.figure()
scat(fig, [key for key, value in liner_data.items() if value == 0], color='g' )
scat(fig, [key for key, value in liner_data.items() if value == 1], color='b' )
# 学習
sample_border = len(train_data)
random.shuffle(train_data)
#mlnn.train(train_data[:20])
mlnn.train(train_data[:sample_border])
# xに対応するyを算出
data = get_predict_list(x_range,y_range, mlnn)
# 学習後分離線
plot(fig, data)
plt.show()
def simple_perceptron():
# simple perceptron
sp = SimplePerceptron( input_neuron_num = 2,
output_neuron_num = 1,
threshold = 1.0,
learning_coefficient = 0.5,
output_function_type = 1)
# train data
x_range = [0,30]
y_range = [0,30]
liner_data = TrainingData.liner_training_data(x_range, y_range)
train_data = TrainingData.change_format(liner_data)
# 教師データのプロット
fig = plt.figure()
scat(fig, [key for key, value in liner_data.items() if value == 0], color='g' )
scat(fig, [key for key, value in liner_data.items() if value == 1], color='b' )
# 学習前分離線
data = get_predict_list(x_range,y_range, sp)
plot(fig, data)
# 学習
sample_border = len(train_data) / 3
random.shuffle(train_data)
for i in range(100):
sp.train(train_data[:sample_border])
# 学習後分離線
data = get_predict_list(x_range,y_range, sp)
plot(fig, data)
plt.show()
def test_change_format(self):
x_range = [0, 1]
y_range = [0, 1]
liner_data = get_training_data.liner_training_data(x_range,y_range)
train_data = get_training_data.change_format(liner_data)
self.assertEquals(train_data, [[[0,1],[1]], [[1,0],[1]], [[0,0],[1]], [[1,1],[1]]])
