Cross Entropy Loss
Cross-entropy loss is a loss function that measures the difference between a predicted probability distribution and the true (target) distribution, commonly used to train classification models.
8 resources across 1 library
Glossary Terms(8)
Learning Rate Scheduling
Learning rate scheduling is the practice of systematically adjusting a model's learning rate during training, rather than keeping it fixed, to speed up converg…
Adam Optimizer
Adam (Adaptive Moment Estimation) is a gradient-based optimization algorithm that maintains per-parameter adaptive learning rates using running estimates of th…
Stochastic Gradient Descent
Stochastic gradient descent (SGD) is an iterative optimization algorithm that updates model parameters using the gradient of the loss computed on a small, rand…
Cross-Entropy Loss
Cross-entropy loss is a loss function that measures the difference between a predicted probability distribution and the true (target) distribution, commonly us…
Mean Squared Error
Mean squared error (MSE) is a loss function that measures the average of the squared differences between predicted and actual values, commonly used to train an…
AUC Score
The AUC score, or Area Under the ROC Curve, is a classification evaluation metric that measures how well a model distinguishes between positive and negative cl…
Data Labeling
Data labeling is the process of assigning informative tags, categories, or ground-truth values to raw data so it can be used to train supervised machine learni…
Data Annotation
Data annotation is the process of enriching raw data with structured metadata — labels, tags, transcriptions, relationships, or attributes — so it can be used…