A loss function that calculates the absolute value of the difference between actual label values and the values that a model predicts. L1 loss is less sensitive to outliers than L2 loss .1
L 1 l o s s = ∑ i = 0 n | y i − y ^ i | where:
n y y ^ y
목차 목차 관련 글 ML crash course - Linear regression 이 글을 인용: “L1 loss: The sum of the absolute values of the difference between the predicted values and the actual values.” Log loss “Squared loss works well for a linear regression where the rate of change of the output values is constant.” Training loss “For example, suppose the loss function is MSE.” 역전파 “The difference between the prediction and the label value is the loss for that example.” ML crash course - Logistic regression “Logistic regression models use log loss as the loss function instead of squared loss.” Test loss “A metric representing a model's loss against the test set.” Mean squared error “The average loss per example when L2 loss is used.” 로지스틱 회귀 “The loss function during training is log loss.” Seeing again: treatment of functional visual loss “There is very little published literature on treatment strategies for functional visual loss.” 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…” Clipping (machine learning) “A technique for handling outliers by doing either or both of the following:” Test set “Because the test set is only indirectly associated with training, test loss is a less biased, higher quality me…” Convex function “A lot of the common loss functions, including the following, are convex functions:” Proxy label “That said, when an actual label is absent, pick the proxy label very carefully, choosing the least horrible pro…” Loss curve “A plot of loss as a function of the number of training iterations.” Iteration (machine learning) “A backward pass (backpropagation) to adjust the model's parameters based on the loss and the learning rate.” Introduction to Machine Learning 관련 절: Definition of [[Machine learning|ML]] 경사하강법 “Move the weight and bias values a small amount in the direction that reduces loss.” Loss (machine learning) “During the training of a supervised learning, a measure of how far a model's prediction is from its label.” Example (machine learning) “A labeled example consists of one or more features and a label.”