Co-evolution

Q: How deeply does Evolutionary Deep Learning: Genetic algorithms and neural networks cover co-evolution?

Demonstrates toolboxes, fitness evaluation, generation control, and mutual population updates without developing evolutionary theory.

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

Coevolution is an evolutionary process or computational technique in which interacting populations or solution components adapt to one another over successive generations.

Co-evolution makes multiple interacting populations adapt together, using evolutionary methods to solve complex problems through cooperating solution components. A practical pairing combines genetic programming (GP), which derives an equation, with a genetic algorithm (GA), which evolves feature-scaling values. section 4.3 section 4.6

A GP–GA regression setup assigns distinct responsibilities to the populations:

Give the GA one scaler gene per input feature; for the Boston housing dataset, that means 13 genes. section 4.3.1

Boston housing regression

A GP-only experiment derives an equation from 13 housing features and can ignore irrelevant inputs, performing feature selection. The co-evolved version adds GA-controlled feature scalers to fine-tune that equation while targeting a fitness score below 135 to encourage a simpler solution. section 4.3.1

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

Cover of Evolutionary Deep Learning: Genetic algorithms and neural networks

liveBook manning.com

Read Evolutionary Deep Learning: Genetic algorithms and neural networks on liveBook Get the book at manning.com

Related concepts

genetic algorithmuses · A genetic algorithm is an evolutionary optimization method that improves a population of candidate solutions through fitness-based selection and variation, often including recombination and mutation.
genetic programminguses · Genetic programming is an evolutionary computation technique that searches over program structures by selecting, recombining, and mutating candidate programs or symbolic expressions.
evolutionary computationuses · Evolutionary computation is a family of search and optimization methods that iteratively improve candidate solutions through variation and selection inspired by biological evolution.

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.