神经网络笔记

神经网络笔记

代码

import numpy as np

# 设置随机种子以获得可重复的结果
np.random.seed(0)

# 定义激活函数及其导数
def sigmoid(x):
    return 1 / (1 + np.exp(-x))

def sigmoid_derivative(x):
    return x * (1 - x)

# 输入数据点
inputs = np.array([[0, 0],
                   [0, 1],
                   [1, 0],
                   [1, 1]])

# 输出数据点
outputs = np.array([[0], [1], [1], [0]])

# 初始化权重和偏置
weights_input_hidden = 2 * np.random.random((2, 4)) - 1
weights_hidden_output = 2 * np.random.random((4, 1)) - 1
bias_hidden = np.zeros((1, 4))
bias_output = np.zeros((1, 1))

# 前向传播
hidden_layer_input = np.dot(inputs, weights_input_hidden) + bias_hidden
hidden_layer_output = sigmoid(hidden_layer_input)

output_layer_input = np.dot(hidden_layer_output, weights_hidden_output) + bias_output
predicted_output = sigmoid(output_layer_input)

# 打印预测输出
print("Predicted Output:")
print(predicted_output)

的神经网络图：

就看三层的神经网络如下

---

前向传播

输入数据点是（0, 0）

隐藏层的权重：
[[ 0.09762701 0.43037873 0.20552675 0.08976637]
[-0.1526904 0.29178823 -0.12482558 0.783546 ]]
输出层的权重：
[[ 0.92732552]
[-0.23311696]
[ 0.58345008]
[ 0.05778984]]
隐藏层的偏置：
[[0. 0. 0. 0.]]
输出层的偏置：
[[0.]]

神经网络的执行过程

先看一个数据的

输入数据点 (0,0) 的计算过程

输入数据点

$\text{inputs}=\left[\begin{array}{cc}0& 0\end{array}\right]$

初始化权重和偏置

输入层到隐藏层的权重:
$\text{weights\_input\_hidden}=\left[\begin{array}{cccc}0.09762701& 0.43037873& 0.20552675& 0.08976637\\ -0.1526904& 0.29178823& -0.12482558& 0.783546\end{array}\right]$

隐藏层到输出层的权重:
$\text{weights\_hidden\_output}=\left[\begin{array}{c}0.92732552\\ -0.23311696\\ 0.58345008\\ 0.05778984\end{array}\right]$

隐藏层的偏置:
$\text{bias\_hidden}=\left[\begin{array}{cccc}0& 0& 0& 0\end{array}\right]$

输出层的偏置:
$\text{bias\_output}=\left[\begin{array}{c}0\end{array}\right]$

前向传播

1. 计算隐藏层的输入:
   $\text{hidden\_layer\_input}=\text{inputs}\cdot \text{weights\_input\_hidden}+\text{bias\_hidden}$

$\text{hidden\_layer\_input}=\left[\begin{array}{cc}0& 0\end{array}\right]\cdot \left[\begin{array}{cccc}0.09762701& 0.43037873& 0.20552675& 0.08976637\\ -0.1526904& 0.29178823& -0.12482558& 0.783546\end{array}\right]+\left[\begin{array}{cccc}0& 0& 0& 0\end{array}\right]$

$\text{hidden\_layer\_input}=\left[\begin{array}{cccc}0& 0& 0& 0\end{array}\right]$

1. 计算隐藏层的输出（使用 sigmoid 激活函数）:
   $\text{hidden\_layer\_output}=\sigma (\text{hidden\_layer\_input})$
   $\sigma (x)=\frac{1}{1+e^{-x}}$

$\text{hidden\_layer\_output}=\left[\begin{array}{cccc}\sigma (0)& \sigma (0)& \sigma (0)& \sigma (0)\end{array}\right]$

$\text{hidden\_layer\_output}=\left[\begin{array}{cccc}0.5& 0.5& 0.5& 0.5\end{array}\right]$

1. 计算输出层的输入:
   $\text{output\_layer\_input}=\text{hidden\_layer\_output}\cdot \text{weights\_hidden\_output}+\text{bias\_output}$

$\text{output\_layer\_input}=\left[\begin{array}{cccc}0.5& 0.5& 0.5& 0.5\end{array}\right]\cdot \left[\begin{array}{c}0.92732552\\ -0.23311696\\ 0.58345008\\ 0.05778984\end{array}\right]+\left[\begin{array}{c}0\end{array}\right]$

$\text{output\_layer\_input}=0.5\cdot 0.92732552+0.5\cdot (-0.23311696)+0.5\cdot 0.58345008+0.5\cdot 0.05778984$

$\text{output\_layer\_input}=0.66772424$

1. 计算最终输出（使用 sigmoid 激活函数）:
   $\text{predicted\_output}=\sigma (\text{output\_layer\_input})$

$\text{predicted\_output}=\sigma (0.66772424)$

$\text{predicted\_output}=\frac{1}{1+e^{-0.66772424}}$

$\text{predicted\_output}\approx 0.66099582$

打印预测输出

Predicted Output for input (0,0):
[[0.66099582]]

下面是全部数据点的计算过程

输入数据点

$$\text{inputs}=\left[\begin{array}{cc}0& 0\\ 0& 1\\ 1& 0\\ 1& 1\end{array}\right]$$

输出数据点

$$\text{outputs}=\left[\begin{array}{c}0\\ 1\\ 1\\ 0\end{array}\right]$$

初始化权重和偏置

$$输入层到隐藏层的权重:\text{weights\_input\_hidden}=\left[\begin{array}{cccc}0.09762701& 0.43037873& 0.20552675& 0.08976637\\ -0.1526904& 0.29178823& -0.12482558& 0.783546\end{array}\right]$$

$$隐藏层到输出层的权重:\text{weights\_hidden\_output}=\left[\begin{array}{c}0.92732552\\ -0.23311696\\ 0.58345008\\ 0.05778984\end{array}\right]$$

$$隐藏层的偏置:\text{bias\_hidden}=\left[\begin{array}{cccc}0& 0& 0& 0\end{array}\right]$$

$$输出层的偏置:\text{bias\_output}=\left[\begin{array}{c}0\end{array}\right]$$

前向传播

1. 计算隐藏层的输入:
   $\text{hidden\_layer\_input}=\text{inputs}\cdot \text{weights\_input\_hidden}+\text{bias\_hidden}$

$\text{hidden\_layer\_input}=\left[\begin{array}{cc}0& 0\\ 0& 1\\ 1& 0\\ 1& 1\end{array}\right]\cdot \left[\begin{array}{cccc}0.09762701& 0.43037873& 0.20552675& 0.08976637\\ -0.1526904& 0.29178823& -0.12482558& 0.783546\end{array}\right]+\left[\begin{array}{cccc}0& 0& 0& 0\end{array}\right]$

$\text{hidden\_layer\_input}=\left[\begin{array}{cccc}0& 0& 0& 0\\ -0.1526904& 0.29178823& -0.12482558& 0.783546\\ 0.09762701& 0.43037873& 0.20552675& 0.08976637\\ -0.05506339& 0.72216696& 0.08070117& 0.87331237\end{array}\right]$

1. 计算隐藏层的输出（使用 sigmoid 激活函数）:
   $$\begin{gathered} \text{hidden\_layer\_output}=\sigma (\text{hidden\_layer\_input}) \\ \sigma (x)=\frac{1}{1+e^{-x}} \end{gathered}$$

$\text{hidden\_layer\_output}=\left[\begin{array}{cccc}\sigma (0)& \sigma (0)& \sigma (0)& \sigma (0)\\ \sigma (-0.1526904)& \sigma (0.29178823)& \sigma (-0.12482558)& \sigma (0.783546)\\ \sigma (0.09762701)& \sigma (0.43037873)& \sigma (0.20552675)& \sigma (0.08976637)\\ \sigma (-0.05506339)& \sigma (0.72216696)& \sigma (0.08070117)& \sigma (0.87331237)\end{array}\right]$

$\text{hidden\_layer\_output}=\left[\begin{array}{cccc}0.5& 0.5& 0.5& 0.5\\ 0.461902& 0.572429& 0.468833& 0.686454\\ 0.524387& 0.605967& 0.551210& 0.522426\\ 0.486237& 0.673110& 0.520163& 0.705455\end{array}\right]$

1. 计算输出层的输入:
   $\text{output\_layer\_input}=\text{hidden\_layer\_output}\cdot \text{weights\_hidden\_output}+\text{bias\_output}$

$\text{output\_layer\_input}=\left[\begin{array}{cccc}0.5& 0.5& 0.5& 0.5\\ 0.461902& 0.572429& 0.468833& 0.686454\\ 0.524387& 0.605967& 0.551210& 0.522426\\ 0.486237& 0.673110& 0.520163& 0.705455\end{array}\right]\cdot \left[\begin{array}{c}0.92732552\\ -0.23311696\\ 0.58345008\\ 0.05778984\end{array}\right]+\left[\begin{array}{c}0\end{array}\right]$

$\text{output\_layer\_input}=\left[\begin{array}{c}0.66772424\\ 0.52997619\\ 0.66047078\\ 0.55106483\end{array}\right]$

1. 计算最终输出（使用 sigmoid 激活函数）:
   $\text{predicted\_output}=\sigma (\text{output\_layer\_input})$

$\text{predicted\_output}=\sigma \left[\begin{array}{c}0.66772424\\ 0.52997619\\ 0.66047078\\ 0.55106483\end{array}\right]$

$\text{predicted\_output}=\left[\begin{array}{c}0.66099582\\ 0.62941358\\ 0.65933295\\ 0.63440526\end{array}\right]$

打印预测输出

Predicted Output:
[[0.66099582]
 [0.62941358]
 [0.65933295]
 [0.63440526]]