PyTorchで学ぶIntroduction to Deep Learning
Jasmin Ludolf
Senior Data Science Content Developer, DataCamp
$$
導関数は「曲線の傾き」を表す
$$
$$

これは凸関数です

これは非凸関数です

$$

$$

$$
3層のネットワークを考える:

# Run a forward pass model = nn.Sequential(nn.Linear(16, 8), nn.Linear(8, 4), nn.Linear(4, 2)) prediction = model(sample)# Calculate the loss and gradients criterion = CrossEntropyLoss() loss = criterion(prediction, target) loss.backward()
# Access each layer's gradients
model[0].weight.grad
model[0].bias.grad
model[1].weight.grad
model[1].bias.grad
model[2].weight.grad
model[2].bias.grad
# Learning rate is typically small lr = 0.001 # Update the weights weight = model[0].weight weight_grad = model[0].weight.gradweight = weight - lr * weight_grad# Update the biases bias = model[0].bias bias_grad = model[0].bias.gradbias = bias - lr * bias_grad
$$
非凸関数には勾配降下法を用いる
PyTorch では オプティマイザで簡略化
import torch.optim as optim # Create the optimizer optimizer = optim.SGD(model.parameters(), lr=0.001)# Perform parameter updates optimizer.step()
PyTorchで学ぶIntroduction to Deep Learning