liveBook · Manning

Dataset

As explained in Deep Learning with Python, Third Edition

Collections of examples used to train or evaluate machine learning models, here including large-scale internet-derived media and text corpora.

A dataset is a collection of examples used to develop and assess a machine learning model. A practical workflow separates it into training, validation, and test data: train on the first, tune configuration against the second, and use the third once for an estimate on unseen, production-like data. section 5.2.1

The split protects evaluation from information leaks. Repeatedly changing layers or other hyperparameters after checking validation performance gradually overfits the validation set, so final evaluation requires a different dataset that has not influenced development. section 5.2.1

How Deep Learning with Python, Third Edition covers it

How deep it goes
Explains split purposes, validation overfitting, information leaks, hold-out validation, and k-fold procedures with code.
Examples
Demonstrates shuffled hold-out splitting and three-fold cross-validation through executable array operations.
What it assumes
Assumes basic familiarity with model training and evaluation while distinguishing hyperparameters from learned parameters.
What you can do after
Apply hold-out or k-fold validation and reserve an untouched test dataset for final evaluation.
How it connects
Connects datasets to model training, hyperparameters, overfitting, information leaks, validation, testing, and production data.
Cover of Deep Learning with Python, Third Edition
liveBookmanning.com
Read Deep Learning with Python, Third Edition on liveBook Get the book at manning.com

Also explained in

Compare how 24 books explain dataset →

Related concepts

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.