liveBook · Manning

Hyperparameter grid

As explained in Evolutionary Deep Learning: Genetic algorithms and neural networks

A parameter grid is a structured collection of predefined values whose Cartesian combinations define configurations for systematic evaluation.

A hyperparameter grid is a predefined set of values whose Cartesian combinations define configurations for systematic evaluation during grid search. Finer cells explore more precisely but expand the search space; larger cells reduce cost while risking local optima. section 5.3.1

Neural-network search configuration

A grid combining middle-layer sizes, learning rates, batch sizes, and epoch counts produces 90 configurations and returns successive parameter combinations for evaluation.

How Evolutionary Deep Learning: Genetic algorithms and neural networks covers it

How deep it goes
Explains generators, grid construction, iteration, reset behavior, configuration sizing, and search-resolution tradeoffs.
Examples
Demonstrates neural-network layer size, learning rate, batch size, and epoch grids producing 90 configurations.
What it assumes
Assumes familiarity with Python classes and generators while demonstrating grid construction from parameter ranges.
What you can do after
Operate/configure a Python grid-search object that generates, enumerates, resets, and evaluates hyperparameter combinations.
How it connects
Connects hyperparameter optimization with grid search, random search, generators, and scikit-learn’s ParameterGrid.
Cover of Evolutionary Deep Learning: Genetic algorithms and neural networks
liveBookmanning.com
Read Evolutionary Deep Learning: Genetic algorithms and neural networks on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Evolutionary Deep Learning: Genetic algorithms and neural networks. The section links point to the parts of the book it draws on.