Loss curve

A plot of loss as a function of the number of training iterations. Loss curves can help you determine when your model is converging or overfitting.¹

Loss curves can plot all of the following types of loss:¹

Footnotes

developers.google.com/machine-learning/glossary#loss-curve ²

ML crash course - Linear regression 이 글을 인용: “When training a model, you'll often look at a loss curve to determine if the model has converged.”
Test set “Because the test set is only indirectly associated with training, test loss is a less biased, higher quality me…”
ML crash course - Logistic regression “Logistic regression models use log loss as the loss function instead of squared loss.”
Log loss “Instead, the loss function for logistic regression is log loss.”
손실 함수 “The goal of training is typically to minimize the loss that a loss function returns.”
역전파 “During the backward pass (backpropagation), the system reduces loss by adjusting the weights of all the neurons…”
A simple way to prevent neural networks from overfitting “Deep neural nets with a large number of parameters are very powerful machine learning systems.”
L1 loss “L1 loss is less sensitive to outliers than L2 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…”
Seeing again: treatment of functional visual loss “There is very little published literature on treatment strategies for functional visual loss.”
L2 loss “Regression models typically use L2 loss as the loss function.”
Early stopping “A method for regularization that involves ending training before training loss finishes decreasing.”
Generalization (machine learning) “To encourage generalization, regularization helps a model train less exactly to the peculiarities of the data i…”
Epoch (machine learning) “An epoch represents N/batch size training iterations, where N is the total number of examples.”
Regularization (machine learning) 관련 절: Training loss vs. real-world performance
경사하강법 “Determine the direction to move the weights and bias that reduce loss.”
Self-training (machine learning) “A variant of self-supervised learning that is particularly useful when all of the following conditions are true:”
Area under the ROC curve “The closer the AUC is to 1.0, the better the model's ability to separate classes from each other.”
ROC curve “AUC: A numerical metric that summarizes the ROC curve into a single floating-point value.”
Introduction to Machine Learning 관련 절: Definition of [[Machine learning|ML]]

See also

Footnotes