liveBook · Manning

Strategy vector

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

A vector of strategy parameters carried by an evolutionary individual to control the mutation and blending applied to its genes.

A strategy vector is an additional vector carried by an evolutionary individual. Its entries control how mutation is applied to the individual’s gene values, allowing mutation strength to adapt during evolution. section 4.4 section 4.4.1

The vector makes evolutionary strategies more adaptive than a fixed mutation rate. Because mutation controls population variability, learning mutation settings over iterations can improve convergence and function approximation. section 4.4.1

Polynomial function approximation

An ES individual can hold six polynomial coefficients while its six-entry strategy vector controls their mutation. The population can be evaluated against polynomial, absolute-value, or step-function data using mean squared error. section 4.4.1

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

How deep it goes
Defines paired vectors and shows DEAP initialization, mutation, blending, bounds checking, and evolutionary execution.
Examples
Uses polynomial, absolute-value, and step functions with six-dimensional individuals and bounded strategy values.
What it assumes
Assumes genetic-algorithm concepts and mutation while introducing strategy vectors as an evolutionary-strategy extension.
What you can do after
Apply it via DEAP to build evolutionary-strategy individuals with adaptive mutation for approximation problems.
How it connects
Connects evolutionary strategies with genetic algorithms, mutation rate, learning rate, and function approximation.
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.