神经元
首先让我们看看神经网络的基本单位,神经元。神经元接受输入,对其做一些数据操作,然后产生输出。例如,这是一个2-输入神经元:
这里发生了三个事情。首先,每个输入都跟一个权重相乘(红色):
然后,加权后的输入求和,加上一个偏差b(绿色):
最后,这个结果传递给一个激活函数f:
激活函数的用途是将一个无边界的输入,转变成一个可预测的形式。常用的激活函数就就是S型函数:
S型函数的值域是(0, 1)。简单来说,就是把(−∞, +∞)压缩到(0, 1) ,很大的负数约等于0,很大的正数约等于1。
一个简单的例子
编码一个神经元
让我们来实现一个神经元!用Python的NumPy库来完成其中的数学计算:
import numpy as np
# 激活函数
# Our activation function: f(x) = 1 / (1 + e^(-x))
def sigmoid(x):
return 1 / (1 + np.exp(-x))
class Neuron:
## 构造函数
def __init__(self,weights,bias):
self.weights = weights
self.bias = bias
## 反馈函数
def feedforward(self,inputs):
# Weight inputs, add bias, then use the activation function
total = np.dot(self.weights,inputs) + self.bias
return sigmoid(total)
weights = np.array([0, 1]) # w1 = 0, w2 = 1
bias = 4
n = Neuron(weights, bias)
x = np.array([2, 3]) # x1 = 2, x2 = 3
print(n.feedforward(x)) # 0.9990889488055994
把神经元组装成网络
所谓的神经网络就是一堆神经元。这就是一个简单的神经网络:
这个网络有两个输入,一个有两个神经元( 和
)的隐藏层,以及一个有一个神经元(
)的输出层。要注意,
的输入就是
和
的输出,这样就组成了一个网络。
例子:前馈
编码神经网络:前馈
接下来我们实现这个神经网络的前馈机制,还是这个图:
import numpy as np
# ... code from previous section here
# 激活函数
# Our activation function: f(x) = 1 / (1 + e^(-x))
def sigmoid(x):
return 1 / (1 + np.exp(-x))
class Neuron:
## 构造函数
def __init__(self,weights,bias):
self.weights = weights
self.bias = bias
## 反馈函数
def feedforward(self,inputs):
# Weight inputs, add bias, then use the activation function
total = np.dot(self.weights,inputs) + self.bias
return sigmoid(total)
class OurNeuralNetwork:
'''
A neural network with:
- 2 inputs
- a hidden layer with 2 neurons (h1, h2)
- an output layer with 1 neuron (o1)
Each neuron has the same weights and bias:
- w = [0, 1]
- b = 0
'''
def __init__(self):
weights = np.array([0, 1])
bias = 0
# The Neuron class here is from the previous section
self.h1 = Neuron(weights, bias)
self.h2 = Neuron(weights, bias)
self.o1 = Neuron(weights, bias)
def feedforward(self, x):
out_h1 = self.h1.feedforward(x)
out_h2 = self.h2.feedforward(x)
# The inputs for o1 are the outputs from h1 and h2
out_o1 = self.o1.feedforward(np.array([out_h1, out_h2]))
return out_o1
network = OurNeuralNetwork()
x = np.array([2, 3])
print(network.feedforward(x)) # 0.7216325609518421
训练神经网络,第1部分
现在有这样的数据:
接下来我们用这个数据来训练神经网络的权重和截距项,从而可以根据身高体重预测性别:
我们用0和1分别表示男性(M)和女性(F),并对数值做了转化:
我这里是随意选取了135和66来标准化数据,通常会使用平均值。
损失
损失计算例子
假设我们的网络总是输出0,换言之就是认为所有人都是男性。损失如何?
代码:MSE损失
下面是计算MSE损失的代码:
import numpy as np
def mse_loss(y_true, y_pred):
# y_true and y_pred are numpy arrays of the same length.
return ((y_true - y_pred) ** 2).mean()
y_true = np.array([1, 0, 0, 1])
y_pred = np.array([0, 0, 0, 0])
print(mse_loss(y_true, y_pred)) # 0.5
如果你不理解这段代码,可以看看NumPy的快速入门中关于数组的操作。
训练神经网络,第2部分
现在我们有了一个明确的目标:最小化神经网络的损失。通过调整网络的权重和截距项,我们可以改变其预测结果,但如何才能逐步地减少损失?
这一段内容涉及到多元微积分,如果不熟悉微积分的话,可以跳过这些数学内容。\
为了简化问题,假设我们的数据集中只有Alice:
那均方差损失就只是Alice的方差:
也可以把损失看成是权重和截距项的函数。让我们给网络标上权重和截距项:
这样我们就可以把网络的损失表示为:
例子:计算偏导数
我们还是看数据集中只有Alice的情况:
把所有的权重和截距项都分别初始化为1和0。在网络中做前馈计算:
网络的输出是 ,对于Male(0)或者Female(1)都没有太强的倾向性。算一下
:
提示:前面已经得到了S型激活函数的导数
。
搞定!这个结果的意思就是增加 ,
也会随之轻微上升。
训练:随机梯度下降
代码:一个完整的神经网络
我们终于可以实现一个完整的神经网络了:
import numpy as np
def sigmoid(x):
# Sigmoid activation function: f(x) = 1 / (1 + e^(-x))
return 1 / (1 + np.exp(-x))
def deriv_sigmoid(x):
# Derivative of sigmoid: f'(x) = f(x) * (1 - f(x))
fx = sigmoid(x)
return fx * (1 - fx)
def mse_loss(y_true, y_pred):
# y_true and y_pred are numpy arrays of the same length.
return ((y_true - y_pred) ** 2).mean()
class OurNeuralNetwork:
'''
A neural network with:
- 2 inputs
- a hidden layer with 2 neurons (h1, h2)
- an output layer with 1 neuron (o1)
*** DISCLAIMER ***:
The code below is intended to be simple and educational, NOT optimal.
Real neural net code looks nothing like this. DO NOT use this code.
Instead, read/run it to understand how this specific network works.
'''
def __init__(self):
# 权重,Weights
self.w1 = np.random.normal()
self.w2 = np.random.normal()
self.w3 = np.random.normal()
self.w4 = np.random.normal()
self.w5 = np.random.normal()
self.w6 = np.random.normal()
# 截距项,Biases
self.b1 = np.random.normal()
self.b2 = np.random.normal()
self.b3 = np.random.normal()
def feedforward(self, x):
# x is a numpy array with 2 elements.
h1 = sigmoid(self.w1 * x[0] + self.w2 * x[1] + self.b1)
h2 = sigmoid(self.w3 * x[0] + self.w4 * x[1] + self.b2)
o1 = sigmoid(self.w5 * h1 + self.w6 * h2 + self.b3)
return o1
def train(self, data, all_y_trues):
'''
- data is a (n x 2) numpy array, n = # of samples in the dataset.
- all_y_trues is a numpy array with n elements.
Elements in all_y_trues correspond to those in data.
'''
learn_rate = 0.1
epochs = 1000 # number of times to loop through the entire dataset
for epoch in range(epochs):
for x, y_true in zip(data, all_y_trues):
# --- Do a feedforward (we'll need these values later)
sum_h1 = self.w1 * x[0] + self.w2 * x[1] + self.b1
h1 = sigmoid(sum_h1)
sum_h2 = self.w3 * x[0] + self.w4 * x[1] + self.b2
h2 = sigmoid(sum_h2)
sum_o1 = self.w5 * h1 + self.w6 * h2 + self.b3
o1 = sigmoid(sum_o1)
y_pred = o1
# --- Calculate partial derivatives.
# --- Naming: d_L_d_w1 represents "partial L / partial w1"
d_L_d_ypred = -2 * (y_true - y_pred)
# Neuron o1
d_ypred_d_w5 = h1 * deriv_sigmoid(sum_o1)
d_ypred_d_w6 = h2 * deriv_sigmoid(sum_o1)
d_ypred_d_b3 = deriv_sigmoid(sum_o1)
d_ypred_d_h1 = self.w5 * deriv_sigmoid(sum_o1)
d_ypred_d_h2 = self.w6 * deriv_sigmoid(sum_o1)
# Neuron h1
d_h1_d_w1 = x[0] * deriv_sigmoid(sum_h1)
d_h1_d_w2 = x[1] * deriv_sigmoid(sum_h1)
d_h1_d_b1 = deriv_sigmoid(sum_h1)
# Neuron h2
d_h2_d_w3 = x[0] * deriv_sigmoid(sum_h2)
d_h2_d_w4 = x[1] * deriv_sigmoid(sum_h2)
d_h2_d_b2 = deriv_sigmoid(sum_h2)
# --- Update weights and biases
# Neuron h1
self.w1 -= learn_rate * d_L_d_ypred * d_ypred_d_h1 * d_h1_d_w1
self.w2 -= learn_rate * d_L_d_ypred * d_ypred_d_h1 * d_h1_d_w2
self.b1 -= learn_rate * d_L_d_ypred * d_ypred_d_h1 * d_h1_d_b1
# Neuron h2
self.w3 -= learn_rate * d_L_d_ypred * d_ypred_d_h2 * d_h2_d_w3
self.w4 -= learn_rate * d_L_d_ypred * d_ypred_d_h2 * d_h2_d_w4
self.b2 -= learn_rate * d_L_d_ypred * d_ypred_d_h2 * d_h2_d_b2
# Neuron o1
self.w5 -= learn_rate * d_L_d_ypred * d_ypred_d_w5
self.w6 -= learn_rate * d_L_d_ypred * d_ypred_d_w6
self.b3 -= learn_rate * d_L_d_ypred * d_ypred_d_b3
# --- Calculate total loss at the end of each epoch
if epoch % 10 == 0:
y_preds = np.apply_along_axis(self.feedforward, 1, data)
loss = mse_loss(all_y_trues, y_preds)
print("Epoch %d loss: %.3f" % (epoch, loss))
# Define dataset
data = np.array([
[-2, -1], # Alice
[25, 6], # Bob
[17, 4], # Charlie
[-15, -6], # Diana
])
all_y_trues = np.array([
1, # Alice
0, # Bob
0, # Charlie
1, # Diana
])
# Train our neural network!
network = OurNeuralNetwork()
network.train(data, all_y_trues)
随着网络的学习,损失在稳步下降。
现在我们可以用这个网络来预测性别了:
# Make some predictions
emily = np.array([-7, -3]) # 128 pounds, 63 inches
frank = np.array([20, 2]) # 155 pounds, 68 inches
print("Emily: %.3f" % network.feedforward(emily)) # 0.951 - F
print("Frank: %.3f" % network.feedforward(frank)) # 0.039 - M
Tensorflow版本
import tensorflow as tf
import numpy as np
data = np.array([
[-2.0, -1], # Alice
[25, 6], # Bob
[17, 4], # Charlie
[-15, -6], # Diana
])
all_y_trues = np.array([
1, # Alice
0, # Bob
0, # Charlie
1, # Diana
])
inputs = tf.keras.Input(shape=(2,))
x = tf.keras.layers.Dense(2, use_bias=True)(inputs)
outputs = tf.keras.layers.Dense(1, use_bias=True, activation='sigmoid')(x)
m = tf.keras.Model(inputs, outputs)
m.compile(tf.keras.optimizers.SGD(learning_rate=0.1), 'mse')
m.fit(data, all_y_trues, epochs=1000, batch_size=1, verbose=0)
emily = np.array([[-7, -3]])
frank = np.array([[20, 2]])
print(m.predict(emily))
print(m.predict(frank))