1001多层感知机从零开始

单层感知机

感知机是一个二分类模型，是最早的AI模型之一

它的求解算法等价于使用批量大小为1的梯度下降

它不能拟合XOR函数，导致第一次AI寒冬

多层感知机

多层感知机使用隐藏层和激活函数来得到非线性模型

常用激活函数是Sigmoid,Tanh,ReLU

超参数：隐藏层数、每层隐藏层的大小

点击查看代码

import torch
from torch import nn
from d2l import torch as d2l

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

# 隐藏层数1 每层隐藏层的大小256
num_inputs, num_outputs, num_hiddens = 784, 10, 256
# 全0或全1会怎样
W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens, requires_grad=True))
# W1 = nn.Parameter(torch.zeros(num_inputs, num_hiddens, requires_grad=True))
# W1 = nn.Parameter(torch.ones(num_inputs, num_hiddens, requires_grad=True))
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
W2 = nn.Parameter(torch.randn(num_hiddens, num_outputs, requires_grad=True))
# W2 = nn.Parameter(torch.zeros(num_hiddens, num_outputs, requires_grad=True))
# W2 = nn.Parameter(torch.ones(num_hiddens, num_outputs, requires_grad=True))
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))
params = [W1, b1, W2, b2]

# 实现ReLU激活函数
def relu(X):
    a = torch.zeros_like(X)
    return torch.max(X, a)

# 感知机模型
def net(X):
    X = X.reshape((-1, num_inputs))
    H = relu(X @ W1 + b1)
    return (H @ W2 + b2)

# 损失函数
loss = nn.CrossEntropyLoss()

# 训练次数、学习率
num_epochs, lr = 3, 0.05
# 优化函数
updater = torch.optim.SGD(params, lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)

W全0或全1会怎样

随机

全0

全1