c++寫完整人工神經網絡,要求輸入層有4個Nodes,一個隱藏層有3個Nodes,輸出層有2個Nodes,要求必須含有反向傳播、梯度下降法更新權重和偏置等。
創建一個簡單的神經網絡如您所描述的，我們需要定義以下幾個部分：
1. 神經網絡的結構
2. 前向傳播（Forward Propagation）
3. 反向傳播（Back Propagation）
4. 更新權重和偏置（梯度下降法）
下面是一個基本的實現：
```
// c++人工神經網絡反向傳播梯度下降更新權重偏置230810a18.cpp : 此文件包含 "main" 函數。程序執行將在此處開始并結束。
#include <iostream>
#include <vector>
#include <cmath>
#include <ctime>
#include <cstdlib>
int Ninpu9t = 9;
int Nhidde12n = 12;// 4;// 11;
int nOutpu2t = 5;// 2;// 3;
// 使用sigmoid作為激活函數
double sigmoid(double x) {
return 1.0 / (1.0 + std::exp(-x));
}
double sigmoid_derivative(double x) {
double s = sigmoid(x);
return s * (1 - s);
}
class NeuralNetwork {
private:
std::vector<std::vector<double>> weights1, weights2; // weights
std::vector<double> bias1, bias2; // biases
double learning_rate;
public:
NeuralNetwork() : learning_rate(0.1) { //01) {
srand(time(nullptr));
// 初始化權重和偏置
weights1.resize(Ninpu9t, std::vector<double>(Nhidde12n));
weights2.resize(Nhidde12n, std::vector<double>(nOutpu2t));
bias1.resize(Nhidde12n);
bias2.resize(nOutpu2t);
for (int i = 0; i < Ninpu9t; ++i)
for (int j = 0; j < Nhidde12n; ++j)
weights1[i][j] = (rand() % 2000 - 1000) / 1000.0; // [-1, 1]
for (int i = 0; i < Nhidde12n; ++i) {//for1100i
bias1[i] = (rand() % 2000 - 1000) / 1000.0; // [-1, 1]
for (int j = 0; j < nOutpu2t; ++j)
weights2[i][j] = (rand() % 2000 - 1000) / 1000.0; // [-1, 1]
}//for1100i
for (int i = 0; i < nOutpu2t; ++i)
bias2[i] = (rand() % 2000 - 1000) / 1000.0; // [-1, 1]
}
std::vector<double> forward(const std::vector<double>& input) {
std::vector<double> hidden(Nhidde12n);
std::vector<double> output(nOutpu2t);
for (int i = 0; i < Nhidde12n; ++i) {//for110i
hidden[i] = 0;
for (int j = 0; j < Ninpu9t; ++j)
{
hidden[i] += input[j] * weights1[j][i];
}
hidden[i] += bias1[i];
hidden[i] = sigmoid(hidden[i]);
}//for110i
for (int i = 0; i < nOutpu2t; ++i) {//for220i
output[i] = 0;
for (int j = 0; j < Nhidde12n; ++j)
{
output[i] += hidden[j] * weights2[j][i];
}
output[i] += bias2[i];
output[i] = sigmoid(output[i]);
}//for220i
return output;
}
void train(const std::vector<double>& input, const std::vector<double>& target) {
// Forward
std::vector<double> hidden(Nhidde12n);
std::vector<double> output(nOutpu2t);
std::vector<double> hidden_sum(Nhidde12n, 0);
std::vector<double> output_sum(nOutpu2t, 0);
for (int i = 0; i < Nhidde12n; ++i) {
for (int j = 0; j < Ninpu9t; ++j)
{
hidden_sum[i] += input[j] * weights1[j][i];
}
hidden_sum[i] += bias1[i];
hidden[i] = sigmoid(hidden_sum[i]);
}//for110i
for (int i = 0; i < nOutpu2t; ++i) {//for220i
for (int j = 0; j < Nhidde12n; ++j)
output_sum[i] += hidden[j] * weights2[j][i];
output_sum[i] += bias2[i];
output[i] = sigmoid(output_sum[i]);
}//for220i
// Backpropagation
std::vector<double> output_errors(nOutpu2t);
for (int i = 0; i < nOutpu2t; ++i)
output_errors[i] = target[i] - output[i];
std::vector<double> d_output(nOutpu2t);
for (int i = 0; i < nOutpu2t; ++i)
d_output[i] = output_errors[i] * sigmoid_derivative(output_sum[i]);
std::vector<double> hidden_errors(Nhidde12n, 0);
for (int i = 0; i < Nhidde12n; ++i) {//for440i
for (int j = 0; j < nOutpu2t; ++j)
hidden_errors[i] += weights2[i][j] * d_output[j];
}//for440i
std::vector<double> d_hidden(Nhidde12n);
for (int i = 0; i < Nhidde12n; ++i)
d_hidden[i] = hidden_errors[i] * sigmoid_derivative(hidden_sum[i]);
// Update weights and biases
for (int i = 0; i < Nhidde12n; ++i) {//for66i
for (int j = 0; j < nOutpu2t; ++j)
weights2[i][j] += learning_rate * d_output[j] * hidden[i];
}//for66i
for (int i = 0; i < nOutpu2t; ++i)
bias2[i] += learning_rate * d_output[i];
for (int i = 0; i < Ninpu9t; ++i) {//for990i
for (int j = 0; j < Nhidde12n; ++j)
weights1[i][j] += learning_rate * d_hidden[j] * input[i];
}//for990i
for (int i = 0; i < Nhidde12n; ++i)
bias1[i] += learning_rate * d_hidden[i];
}//void train(const std::vector<double>& input, const std::vector<double>& target
}; //class NeuralNetwork {
int main() {
NeuralNetwork nn;
// Example
std::vector<double> input[5];
input[0] = { 0,1,0, 0,1,0, 0,1,0 }; //1{ 1.0, 0.5, 0.25, 0.125 };
input[1] = { 0,0,0, 1,1,1,0,0,0 }; //-{ 1.0, 0.5, 0.25, 0.125 };
input[2] = { 0,1,0, 1,1,1, 0,1,0 }; //+{ 1.0, 0.5, 0.25, 0.125 };
input[3] = { 0,1,0, 0,2, 0, 0, 3, 0.12 }; // 'O'或 '[]'型號{ 1.0, 0.5, 0.25, 0.125 };
input[4] = { 1,1,0, 9,0,9.8, 1,1,1 }; //+{ 1.0, 0.5, 0.25, 0.125 };
std::vector<double> target[5];
target[0] = { 1.0, 0,0,0,0 };// , 0}; //0.0, 1.0, 0.5}; //{ 0.0, 1.0 };
target[1] = { 0,1.0 ,0,0,0};// 91.0, 0};// , 0, 0}; //
target[2] = { 0,0,1,0,0 };// 1.0, 0.5};
target[3] = { 1,0,0,1,0};
target[4] = { 0,0,0,0,5 };
// Training
for (int i = 0; i < 10000/*00 */; ++i) {//for220i
for (int jj = 0; jj < 4; ++jj) {
nn.train(input[jj], target[jj]);
}
}//for220i
// Test
input[0] = { 0,1,0, 0,1,0, 0,1,0 }; //1{ 1.0, 0.5, 0.25, 0.125 };
std::vector<double> output = nn.forward(input[0]);
for (auto& val : output)
std::cout << val << " ";
std::cout << std::endl;
input[1] = { 0,0,0, 1,1,1, 0,0,0 };
//std::vector<double>
output = nn.forward(input[1]);
for (auto& val : output)
std::cout << val << " ";
return 0;
}//main
```
運行結果：
0.978955 0.00350907 0.0190363 0.0246372 0.00523369
0.00402561 0.981827 0.0193466 6.64613e-05 0.00696526
F:\嘗試加多輸入c++神經網絡反向傳播梯度下降更新權重偏置230810a18\x64\Debug\c++人工神經網絡反向傳播梯度下降更新權重偏置230810a18.exe
