多层感知机(MLP)是早期就出现的神经网络,拥有一层隐藏层,但由于没有非线性的激活函数,即使2层也只是做线性映射,功效与单层输出的神经网络差不多,本节将介绍MLP的基本概念以及如何解决MLP存在的缺陷。
MLP
- 隐藏层
形式化如下:
H = X W h + B h O = H W o + B o = X W h W o + B h W o + B o H=XW_h+B_h \\ O=HW_o+B_o=XW_hW_o+B_hW_o+B_o H=XWh+BhO=HWo+Bo=XWhWo+BhWo+Bo
从公式可以看出,虽然神经网络引入了隐藏层,却依然等价于一个单层神经网络。要解决这个问题,需要引入激活函数,做非线性映射。 - 激活函数
常见的3个激活函数:ReLU/Sigmoid/tanh
R e L U ( x ) = m a x ( x , 0 ) ReLU(x)=max(x,0) ReLU(x)=max(x,0)
S i g m o i d ( x ) = 1 1 + e − x Sigmoid(x)=\frac{1}{1+e^{-x}} Sigmoid(x)=1+e−x1
t a n h ( x ) = 1 − e − 2 x 1 + e − 2 x tanh(x)=\frac{1-e^{-2x}}{1+e^{-2x}} tanh(x)=1+e−2x1−e−2x
- MLP
改进后的MLP就是含有至少一个隐藏层的由全连接层组成的神经网络,且每个隐藏层的输出都要通过非线性的激活函数进行变换。
从0实现
- 加载数据集
import torch
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size,root='/home/kesci/input/FashionMNIST2065')
- 初始化参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)
params = [W1, b1, W2, b2]
for param in params:
param.requires_grad_(requires_grad=True)
- 定义模型
def relu(X):
return torch.max(input=X, other=torch.tensor(0.0))
def net(X):
X = X.view((-1, num_inputs))
H = relu(torch.matmul(X, W1) + b1)
return torch.matmul(H, W2) + b2
- 定义损失函数
loss = torch.nn.CrossEntropyLoss()
-
定义优化函数
SGD函数
-
训练模型并预测
num_epochs, lr = 5, 100.0
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params=None, lr=None, optimizer=None):
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y).sum()
# 梯度清零
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
d2l.sgd(params, lr, batch_size)
else:
optimizer.step() # “softmax回归的简洁实现”一节将用到
train_l_sum += l.item()
train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
n += y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)
pytorch实现
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
num_inputs, num_outputs, num_hiddens = 784, 10, 256
net = nn.Sequential(
d2l.FlattenLayer(),
nn.Linear(num_inputs, num_hiddens),
nn.ReLU(),
nn.Linear(num_hiddens, num_outputs),
)
for params in net.parameters():
init.normal_(params, mean=0, std=0.01)
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size,root='/home/kesci/input/FashionMNIST2065')
loss = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.5)
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)
有话要说
一些问题:
- 激活函数的作用?三种激活函数的优缺点?如何选择合适的激活函数?
- 多层感知机就是指仅有一个隐藏层的神经网络吗?