Go back to the [[AI Glossary]]
The fraction of predictions that a classification model got right. In multi-class classification, accuracy is defined as follows: $$Accuracy = \frac{Correct Predictions}{Total Number of Examples} $$
In binary classification, accuracy has the following definition:
$$Accuracy = \frac{True Positives + True Negatives}{Total Number of Examples} $$
See true positive and true negative.