A loss function that calculates the square of the difference between actual label values and the values that a model predicts. Due to squaring, L2 loss amplifies the influence of outliers . That is, L2 loss reacts more strongly to bad predictions than L1 loss .1
L 2 l o s s = ∑ i = 0 n ( y i − y ^ i ) 2 목차 목차 관련 글 ML crash course - Linear regression 이 글을 인용: “L2 loss: The sum of the squared difference between the predicted values and the actual values.” Log loss 이 글을 인용: “Squared loss works well for a linear regression where the rate of change of the output values is constant.” ML crash course - Logistic regression 이 글을 인용: “Explain why logistic regression uses log loss instead of squared loss.” Training loss “For example, suppose the loss function is MSE.” 로지스틱 회귀 “The loss function during training is log loss.” Convex function “A lot of the common loss functions, including the following, are convex functions:” Test loss “When building a model, you typically try to minimize test loss.” 역전파 “The difference between the prediction and the label value is the loss for that example.” Seeing again: treatment of functional visual loss “There is very little published literature on treatment strategies for functional visual loss.” Mean absolute error “The average loss per example when L1 loss is used.” Clipping (machine learning) “Outliers can damage models, sometimes causing weights to overflow during training.” Test set “Because the test set is only indirectly associated with training, test loss is a less biased, higher quality me…” mini-batch “It is much more efficient to calculate the loss on a mini-batch than the loss on all the examples in the full b…” Loss curve “A plot of loss as a function of the number of training iterations.” Introduction to Machine Learning 관련 절: Definition of [[Machine learning|ML]] Sigmoid function “Converting the raw output of a logistic regression or multinomial regression model to a probability.”