Loss (machine learning)

During the training of a supervised learning, a measure of how far a model’s prediction is from its label. A loss function calculates the loss.¹

Footnotes

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

ML crash course - Linear regression 이 글을 인용: “The goal of training a model is to minimize the loss, reducing it to its lowest possible value.”
역전파 이 글을 인용: “The difference between the prediction and the label value is the loss for that example.”
Training loss 이 글을 인용: “For example, suppose the loss function is MSE.”
Introduction to Machine Learning 관련 절: Definition of [[Machine learning|ML]]
Iteration (machine learning) 이 글을 인용: “A backward pass (backpropagation) to adjust the model's parameters based on the loss and the learning rate.”
Self-training (machine learning) “A variant of self-supervised learning that is particularly useful when all of the following conditions are true:”
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.”
Machine Learning Systems “Machine Learning Systems provides a systematic framework for understanding and engineering machine learning (ML…”
Semi-supervised learning “Self-training is one technique for semi-supervised learning.”
모델 (기계학습) “In supervised machine learning, a model takes an example as input and infers a prediction as output.”
수렴 (기계학습) 이 글을 인용: “During a long period of constant loss values, you may temporarily get a false sense of convergence.”
Generalization (machine learning) “To encourage generalization, regularization helps a model train less exactly to the peculiarities of the data i…”
경사하강법 이 글을 인용: “Gradient descent is older--much, much older--than machine learning.”
Log loss “Instead, the loss function for logistic regression is log loss.”
Epoch (machine learning) “The number of epochs is a hyperparameter you set before the model begins training.”
L1 loss “A loss function that calculates the absolute value of the difference between actual label values and the values…”
Downsampling (machine learning) “For example, before training an image recognition model, downsampling high-resolution images to a lower-resolut…”
Example (machine learning) “Examples in supervised learning fall into two general categories:”
기계학습 “2024-08-24 - What's Really Going On in Machine Learning?”
Test set “Because the test set is only indirectly associated with training, test loss is a less biased, higher quality me…”