Validation loss

A metric representing a model’s loss on the validation set during a particular iteration of training.¹

Footnotes

developers.google.com/machine-learning/glossary#validation-loss

Test set 이 글을 인용: “The training set and validation set are both closely tied to training a model.”
Test loss 이 글을 인용: “That's because a low test loss is a stronger quality signal than a low training loss or low validation loss.”
ML crash course - Linear regression “The loss curve shows how the loss changes as the model trains.”
Training loss “A metric representing a model's loss during a particular training iteration.”
Early stopping “In early stopping, you intentionally stop training the model when the loss on a validation dataset starts to in…”
mini-batch “Therefore, each iteration determines the loss on a random 20 of the 1,000 examples and then adjusts the weights…”
Loss curve “A plot of loss as a function of the number of training iterations.”
역전파 “During the backward pass (backpropagation), the system reduces loss by adjusting the weights of all the neurons…”
Log loss “Squared loss works well for a linear regression where the rate of change of the output values is constant.”
L1 loss “L1 loss is less sensitive to outliers than L2 loss.”
손실 함수 “The goal of training is typically to minimize the loss that a loss function returns.”
Introduction to Machine Learning 관련 절: Definition of [[Machine learning|ML]]
Generalization (machine learning) “To encourage generalization, regularization helps a model train less exactly to the peculiarities of the data i…”
Self-training (machine learning) “Notice that each iteration of Step 2 adds more labeled examples for Step 1 to train on.”
Epoch (machine learning) “The number of epochs is a hyperparameter you set before the model begins training.”
학습 데이터 “For example, a single example shouldn't belong to both the training set and the validation set.”
L2 loss “That is, L2 loss reacts more strongly to bad predictions than L1 loss.”
Machine Learning Systems “Machine Learning Systems provides a systematic framework for understanding and engineering machine learning (ML…”
수렴 (기계학습) “A state reached when loss values change very little or not at all with each iteration.”
경사하강법 “A mathematical technique to minimize loss.”

See also

Footnotes