Discontinuous function

Q: How deeply does Evolutionary Deep Learning: Genetic algorithms and neural networks cover discontinuous function?

Explains component-wise mutation, fitness testing, and replacement through executable notebook experiments.

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

A discontinuous function is a function whose output has a jump, break, or other noncontinuous change as its input varies.

A discontinuous function changes through a jump, break, or other noncontinuous transition. Differential Evolution (DE) is used to approximate such functions because it compares agent components individually instead of relying on global gradient optimization. section 4.5.1

A DE approximation proceeds by repeatedly:

Selecting three random agents and combining the first with a scaled, component-wise difference between the other two. section 4.5.1
Evaluating the modified agent and replacing the target when the new fitness is better. section 4.5.1
Changing the function type and runtime in a notebook to compare approximation behavior on polynomial, absolute, and step functions. section 4.5.1

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

differential evolutionaddressed by · Differential evolution is a population-based optimization algorithm that generates trial solutions by combining scaled differences between existing candidate solutions.
continuous functioncontrasts with · A function whose output changes arbitrarily little when its input changes arbitrarily little.

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.