深度学习（非线性优化）

import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np

a = [1.0, 2.0, 1.0]
x = np.linspace(start=0, stop=1, num=100)
y = np.exp(a[0]*x*x+a[1]*x+a[2])

par = torch.tensor([0.0, 0.0, 0.0], requires_grad=True)

x = torch.tensor(x)
y = torch.tensor(y)

optimizer = optim.Adam([par], lr=0.4)
lossfun = nn.MSELoss()

for step in range(1000):
    # 前向传播
    outputs = torch.exp(par[0]*x*x+par[1]*x+par[2])
    loss = lossfun(outputs, y)

    # 反向传播和优化
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    if step % 10==0:
        print(loss.item())

print('result:', par.detach().numpy())