KerasTuner
KerasTuner is a library for defining, running, and evaluating automated searches for effective hyperparameter configurations of Keras models.
Deep Learning with R, Third Edition
KerasTuner is a library for defining, running, and evaluating hyperparameter searches for Keras models.
- How it is used
- Automates the search for effective Keras model configurations when training each candidate is expensive and hyperparameters are not differentiable.
- How deep it goes
- Defines search spaces, model builders, tuners, objectives, trials, validation, early stopping, and final model selection.
- Examples
- Uses an MNIST dense classifier whose units and optimizer vary across trials, with validation accuracy guiding selection.
- What you can do after
- Apply it via KerasTuner to define searches, run trials, retrieve top configurations, retrain models, and evaluate them on test data.
Read how Deep Learning with R, Third Edition explains KerasTuner →
Deep Learning with Python, Third Edition
A Keras-related library for automating hyperparameter search over model configurations.
- How it is used
- Automates searching Keras model configurations when manually selecting hyperparameters is expensive and repetitive.
- How deep it goes
- Explains search spaces, model builders, tuners, objectives, trials, and result retrieval, but does not derive optimization theory.
- Examples
- Uses an MNIST multilayer perceptron that searches dense-layer units, optimizer choice, validation accuracy, training epochs, and final test performance.
- What you can do after
- Apply it via KerasTuner to define a search space, run trials, and select or retrain promising Keras models.
Read how Deep Learning with Python, Third Edition explains KerasTuner →
Distributed Machine Learning Patterns
Keras Tuner is a library for searching and selecting hyperparameter configurations for Keras models.
- How it is used
- Uses automated hyperparameter search to improve Keras model selection beyond a single manually chosen configuration.
- How deep it goes
- Explains installation, model construction, tuner configuration, search, selection, retraining, and evaluation without detailing tuner internals.
- Examples
- Demonstrates MNIST tuning with dense-layer width, Adam learning rate, Hyperband, validation splitting, and test-set evaluation.
- What you can do after
- Apply KerasTuner to define a search space, run Hyperband, retrieve the best hyperparameters, retrain, and evaluate a model.
Read how Distributed Machine Learning Patterns explains KerasTuner →
What to know first
- backpropagationBackpropagation is reverse-mode differentiation that propagates derivatives backward through a computational graph to compute gradients of an output or loss with respect to inputs and parameters.
- epochAn epoch is one complete pass through the training data during model training.
- float16float16 is a 16-bit floating-point format, commonly IEEE 754 binary16, with less precision and range than 32-bit floating-point formats.
- random searchRandom search is an optimization technique that explores a search space by randomly selecting and evaluating candidate solutions or configurations.
Related concepts
- hyperparameter tuningused by · Hyperparameter tuning is the systematic selection of configurable model or learning-procedure settings by evaluating alternatives against a chosen objective.
- hyperparameteruses · A hyperparameter is a setting chosen outside ordinary parameter learning that controls a model, algorithm, or learning procedure.
Questions about KerasTuner
What is KerasTuner?
KerasTuner is a library for defining, running, and evaluating automated searches for effective hyperparameter configurations of Keras models.
Which Manning books explain KerasTuner?
Deep Learning with R, Third Edition, Deep Learning with Python, Third Edition and Distributed Machine Learning Patterns.
What should I know before learning KerasTuner?
Manning books that teach KerasTuner usually introduce backpropagation, epoch, float16 and random search first.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.


