深度学习笔记（一）

最近工作需要用到深度学习，之前仅有一些python基础（也忘得差不多了），于是找到教程 零基础入门深度学习准备快速上手。第一部分是使用python训练一个感知器（即网络中的神经元）模型，原文中使用python2.7实现，改为了python3.6，未加载numpy库。

from functools import reduce

class Perception(object):
    def __init__(self, input_num, activator):
        '''
        初始化感知器，设置输入参数的个数以及激活函数
        输出公式：y = f ( w * x + b )
        '''
        self.activator= activator #'初始化激活函数'
        self.weights = [ 0.0 for _ in range (input_num) ] #'权重和输入维度相同'
        self.bias = 0.0 #'偏置b初始化为0'
        
    def __str__(self):
        #'打印学习到的权重w和偏置项b'
        return 'weights\t:%s\nbias\t:%f\n' % (self.weights, self.bias)
    
    def predict (self, input_vec):
        #'输入向量x，输出感知器的计算结果'
        return self.activator(
                reduce (lambda a, b: a + b,
                        list(map(lambda x: x[0] * x[1],
                            list(zip(input_vec, self.weights))))
                        , 0.0) + self.bias)
                        
    def train (self, input_vecs, labels, iteration, rate):
        for i in range(iteration):
            self._one_iteration(input_vecs, labels, rate)
    
    def _one_iteration(self, input_vecs, labels, rate):
        #'label为实际值'
        samples = zip(input_vecs, labels)
        for (input_vec,label) in samples:
            output = self.predict(input_vec) #'计算更新后的y值'
            self._update_weights(input_vec, output, label, rate) #'更新权值w'
    
    def _update_weights(self, input_vec, output, label, rate):
        
        delta = label - output
        self.weights = list(map(
                lambda x: x[1] + rate * delta * x[0], #'wi = wi + wi''
                list(zip (input_vec, self.weights))
                ))
        self.bias += rate * delta
    
    '''
    一个感知器（神经元）模型
    '''
def f(x):
    return 1 if x > 0 else 0 #'定义激活函数为阶跃函数'

def get_training_dataset():
    #'基于and真值表构建训练数据'
    input_vecs = [[1,1], [0,0], [1,0],[0,1]]
    labels = [1,0,0,0]
    return input_vecs, labels

def train_and_perception():
    #'使用and真值表训练感知器'
    p = Perception (2,f) #'input_num & activator'
    input_vecs, labels = get_training_dataset()
    p.train (input_vecs, labels, 10, 0.1)
    return p

if __name__ == '__main__':
    and_perception = train_and_perception()
    print (and_perception)
    
    print ('1 and 1 = %d' % and_perception.predict([1,1]))
    print ('0 and 0 = %d' % and_perception.predict([0,0]))
    print ('1 and 0 = %d' % and_perception.predict([1,0]))
    print ('0 and 1 = %d' % and_perception.predict([0,1]))  

打印更新后的权值、偏置和输出。

weights :[0.1, 0.2]
bias    :-0.200000

1 and 1 = 1
0 and 0 = 0
1 and 0 = 0
0 and 1 = 0