Back to the Index

Train (Training) Set

What is a train set?

The train (or training) set is the portion of the training data that is used to train a machine learning model. It typically consists of 70-85% of the total available training data. It is essential to ensure that the training set is representative of the problem domain and includes a diverse set of examples. To maintain the integrity of the training process and avoid overfitting, it is essential to keep the training set separate from the validation and test sets. These other sets are used to fine-tune the model's hyperparameters and evaluate its performance on unseen data, respectively.

Does this content look outdated? If you are interested in helping us maintain this, feel free to contact us.

© Hopsworks 2024. All rights reserved. Various trademarks held by their respective owners.

Privacy Policy
Cookie Policy
Terms and Conditions