# Glossary

# Glossary¶

- Accuracy¶
Evaluation metrix measuring the fraction of predictions that a classification model got right (Wikipedia).

- Activation function¶
A function (for example, ReLU or sigmoid) that generates a (typically nonlinear) output. Used in neural networks to define the output of a layer (Wikipedia).

- AUROC¶
Area Under the ROC Curve. An aggregate measure of a classifier’ performance across all possible classification thresholds (Wikipedia).

- Automatic differentiation (autodiff)¶
Soon!

- Backpropagation¶
Mathematical technique used to obtain the gradients of the loss function with respect to the weights of a neural network. Applies the chain rule to compute the gradients one layer at a time, iterating backwards from the output layer (Wikipedia).

- Batch¶
A set of examples used in one iteration (that is, one gradient update) during model training. Batch size defines the number of examples in a batch (Wikipedia).

- Bias¶
Soon!

- Boosting¶
Soon!

- Broadcasting¶
Soon!

- Confusion matrix¶
Soon!

- Decision boundary¶
Frontier between the classes learned by a classification model.

- Precision¶
Evaluation matrix measuring the frequency with which a model was correct when predicting the positive class (Wikipedia).

- Self-supervised learning¶
Form of Machine Learning in which labels are automatically generated from the data itself, then a model is supervisely trained on the resulting dataset.