The architecture of AlexNet can be implemented in modern deep learning frameworks like PyTorch by sequentially composing convolutional, pooling, and fully connected layers. The network starts with a large $11 \times 11$ convolution with a stride of $4$, followed by ReLU activations and max-pooling operations. It then processes the feature maps through smaller $5 \times 5$ and $3 \times 3$ convolutions. Finally, the tensor is flattened and passed through two $4096$-dimensional fully connected layers, where dropout ($p=0.5$) is applied to prevent overfitting.

class AlexNet(d2l.Classifier):
    def __init__(self, lr=0.1, num_classes=10):
        super().__init__()
        self.save_hyperparameters()
        self.net = nn.Sequential(
            nn.LazyConv2d(96, kernel_size=11, stride=4, padding=1),
            nn.ReLU(), nn.MaxPool2d(kernel_size=3, stride=2),
            nn.LazyConv2d(256, kernel_size=5, padding=2), nn.ReLU(),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.LazyConv2d(384, kernel_size=3, padding=1), nn.ReLU(),
            nn.LazyConv2d(384, kernel_size=3, padding=1), nn.ReLU(),
            nn.LazyConv2d(256, kernel_size=3, padding=1), nn.ReLU(),
            nn.MaxPool2d(kernel_size=3, stride=2), nn.Flatten(),
            nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(p=0.5),
            nn.LazyLinear(4096), nn.ReLU(), nn.Dropout(p=0.5),
            nn.LazyLinear(num_classes))
        self.net.apply(d2l.init_cnn)