一、
1、感知机可以描述为一个线性方程，用python的伪代码可表示为：
sum(weight_i * x_i) + bias -> activation #activation表示激活函数，x_i和weight_i是分别为与当前神经元连接的其它神经元的输入以及连接的权重。bias表示当前神经元的输出阀值（或称偏置）。箭头(->)左边的数据，就是激活函数的输入
2、定义激活函数f:
def func_activator(input_value):
return 1.0 if input_value >= 0.0 else 0.0
二、感知机的构建
class Perceptron(object):
def __init__(self, input_para_num, acti_func):
self.activator = acti_func
self.weights = [0.0 for _ in range(input_para_num)]
def __str__(self):
return 'final weights w0 = {:.2f} w1 = {:.2f} w2 = {:.2f}'
.format(self.weights[0],self.weights[1],self.weights[2])
def predict(self, row_vec):
act_values = 0.0
for i in range(len(self.weights)):
act_values += self.weights [ i ] * row_vec [ i ]
return self.activator(act_values)
def train(self, dataset, iteration, rate):
for i in range(iteration):
for input_vec_label in dataset:
prediction = self.predict(input_vec_label)
self._update_weights(input_vec_label,prediction, rate)
def _update_weights(self, input_vec_label, prediction, rate):
delta = input_vec_label[-1] - prediction
for i in range(len(self.weights):
self.weights[ i ] += rate * delta * input_vec_label[ i ]
def func_activator(input_value):
return 1.0 if input_value >= 0.0 else 0.0
def get_training_dataset():
dataset = [[-1, 1, 1, 1], [-1, 0, 0, 0], [-1, 1, 0, 0], [-1, 0, 1, 0]]
return dataset
def train_and_perceptron():
p = Perceptron(3, func_activator)
dataset = get_training_dataset()
return p
if __name__ == '__main__':
and_prerception = train_and_perceptron
print(and_prerception)
print('1 and 1 = %d' % and_perception.predict([-1, 1, 1]))
print('0 and 0 = %d' % and_perception.predict([-1, 1, 1]))
print('1 and 0 = %d' % and_perception.predict([-1, 1, 1]))
print('0 and 1 = %d' % and_perception.predict([-1, 1, 1]))