Concept均方误差 / Mean Squared Error / L2损失
MSE Loss
One of the most commonly used regression loss functions in machine learning, computed as the mean of squared differences between predicted and true values. It corresponds to a Gaussian noise assumption and is known to be sensitive to outliers.
Timeline (last 90 days)
Sep 12
From epoch 160 to epoch 290, the MSE loss decreased from 0.0690 to 0.0652, a drop of only approximately 0.006 over 130 epochs.
Unverified50%
Sep 12
MSE loss tends to produce blurry results to minimize pixel-level error, while perceptual loss (LPIPS) can better measure visual similarity.
Unverified50%