Generation
A generation is a stage or iteration in an evolutionary process, associated with a population of candidate solutions or organisms.
Advanced Algorithms and Data Structures
A generation is one successive stage of a population in an evolutionary process.
- How it is used
- Frames each genetic-algorithm iteration as a population transition toward better solutions.
- How deep it goes
- Defines generations and explains their population transition, but defers detailed operator implementations beyond selection pseudocode.
- Examples
- Uses knapsack food selections and population-transition diagrams to illustrate generations.
- What you can do after
- Apply generations to interpret how genetic algorithms repeatedly replace candidate populations with newly created solutions.
Read how Advanced Algorithms and Data Structures explains generation →
Classic Computer Science Problems in Swift: Essential techniques for practicing programmers
A generation is one evolutionary cycle in which a genetic algorithm evaluates and transforms a population of candidate solutions.
- How it is used
- Uses generations to organize repeated evaluation and transformation of candidate solutions in a genetic algorithm.
- How deep it goes
- Explains generation-level evaluation, selection, reproduction, mutation, thresholds, and progress reporting without formal evolutionary analysis.
- Examples
- Uses SimpleEquation progress logs and a SEND+MORE=MONEY run completed in 38 generations.
- What you can do after
- Apply it via GeneticAlgorithm to monitor progress and solve maximization or constraint problems.
Evolutionary Deep Learning: Genetic algorithms and neural networks
A generation is one complete iteration of population variation, evaluation, and selection in an evolutionary algorithm.
- How it is used
- Uses repeated population-level iterations to evolve solutions and determine when an evolutionary algorithm should stop.
- How deep it goes
- Explains the full operational loop and runnable statistics, while deferring advanced multi-generation breeding details.
- Examples
- Demonstrates generations through a one-max binary simulation and a life simulation optimizing traits a, b, and c.
- What you can do after
- Apply generations via Python loops to run evolutionary simulations and inspect population fitness distributions.
Read how Evolutionary Deep Learning: Genetic algorithms and neural networks explains generation →
Also covered in
What to know first
- crossoverCrossover is an evolutionary recombination technique that combines material from parent candidate solutions to produce one or more offspring.
- evolutionary computationEvolutionary computation is a family of search and optimization methods that iteratively improve candidate solutions through variation and selection inspired by biological evolution.
- individualAn individual is a single candidate solution represented as a member of an evolutionary algorithm's population and evaluated by its fitness.
- offspringOffspring are new candidate individuals or solutions produced from one or more parent candidates through reproduction or variation.
Related concepts
- epochequivalent to · An epoch is one complete pass through the training data during model training.
Questions about generation
What is generation?
A generation is a stage or iteration in an evolutionary process, associated with a population of candidate solutions or organisms.
Which Manning books explain generation?
Advanced Algorithms and Data Structures, Classic Computer Science Problems in Swift: Essential techniques for practicing programmers and Evolutionary Deep Learning: Genetic algorithms and neural networks.
What should I know before learning generation?
Manning books that teach generation usually introduce crossover, evolutionary computation, individual and offspring 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.


