In machine learning, an epoch refers to one complete pass of the entire training dataset through the learning algorithm. In other words, it is when all the training data is used at once, and the algorithm updates its internal model parameters based on the entire dataset. An epoch is comprised of one or more batches, where a batch is a subset of the training data that is used to update the model parameters. The number of epochs is a hyperparameter that determines the number of times the entire dataset is worked through the learning algorithm. The number of epochs is traditionally large, often hundreds or thousands, allowing the learning algorithm to run until the error from the model has been sufficiently minimized. However, there is no guarantee that a network will converge or improve by letting it learn the data for multiple epochs. The term "epoch" is also used in other contexts, such as in geology, where it refers to a period of time of variable length that is a portion of a period.