How deeply does Deep Learning with Python, Third Edition cover hold-out validation?

Explains the split, training, evaluation, retraining, and small-data caveat, then defers repeated partitioning to K-fold methods.

Hold-out validation

As explained in Deep Learning with Python, Third Edition

An evaluation protocol that splits data once into separate subsets for training, validation, and/or testing.

Hold-out validation reserves part of a dataset, trains on the remainder, and evaluates on the reserved data. Keep a separate, untouched test set when tuning models. section 5.2.1

A simple split

Shuffle the data, set aside a validation slice, train on the remaining samples, and evaluate on the slice. After choosing the model, retrain with training and validation data combined, then measure generalization once on the untouched test set. section 5.2.1

Use these practical checks:

Treat unstable scores across different random splits as a warning that the validation or test sets are not representative. section 5.2.1
Prefer K-fold or iterated K-fold validation when limited data makes a single split unreliable. section 5.2.1

How Deep Learning with Python, Third Edition covers it

Cover of Deep Learning with Python, Third Edition

liveBook manning.com

Read Deep Learning with Python, Third Edition on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Deep Learning with R, Third EditionHold-out validation is an evaluation procedure that reserves a subset of available data for assessment without using it to fit the model.

Compare how 2 books explain hold-out validation →

Related concepts

cross-validationalternative to · Cross-validation is a resampling technique that evaluates a model by repeatedly fitting it on some portions of available data and assessing it on held-out portions.
validationkind of · The process of checking data, behavior, systems, models, or results against defined criteria to assess their correctness, suitability, or acceptability.
evaluation datasetuses · An evaluation dataset is a collection of examples or test cases, often with expected or judged outcomes, designated to assess a model or system against defined criteria.
training datasetimplements · A collection of examples or observations supplied to a learning procedure to fit or adapt a model or learn its patterns or parameters.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with Python, Third Edition. The section links point to the parts of the book it draws on.