Evolutionary computation
Evolutionary computation is a family of search and optimization methods that iteratively improve candidate solutions through variation and selection inspired by biological evolution.
Evolutionary Deep Learning: Genetic algorithms and neural networks
An evolutionary optimizer is an optimization algorithm that searches candidate configurations through population-based variation and selection.
- How it is used
- Automates and optimizes deep-learning development across data, validation, hyperparameters, model options, and architectures.
- How deep it goes
- Defines populations and fitness, then develops simulations, differential evolution, and DEAP-based particle-search implementations without formal proofs.
- Examples
- Uses Conway’s Game of Life, continuous and discontinuous function approximation, CNN layer experiments, and DEAP particle-based hyperparameter tuning.
- What you can do after
- Apply it via DEAP to encode, evaluate, and iteratively improve deep-learning hyperparameter configurations.
Optimization Algorithms: AI techniques for design, planning, and control problems
Evolutionary computation is a family of computational methods inspired by biological evolution that iteratively improves candidate solutions through variation and selection.
- How it is used
- Introduces evolutionary computation as a population-based approach to finding optimal or near-optimal solutions.
- How deep it goes
- Explains population initialization, fitness, selection, and genetic operators, then develops the binary-coded genetic algorithm in Python.
- Examples
- Uses a treasure-hunting team analogy and compares population initialization strategies.
- What you can do after
- Build a binary-coded genetic algorithm in Python and evaluate population-size choices through experimentation.
Self-Improving Agents
A search method that improves candidate solutions through variation and selection across iterations.
- How it is used
- Uses population search to generate candidate agent-artifact improvements when a single hill-climber stalls.
- How deep it goes
- Works through a Python fitness-and-mutation loop, then compares population and archive strategies without a formal derivation.
- Examples
- Demonstrates eight integers evolving toward 73 and compares GEPA and DGM through recorded generations and failures.
- What you can do after
- Build it from scratch as an integer-search loop, then evaluate population and archive choices for scored artifact improvement.
Read how Self-Improving Agents explains evolutionary computation →
Grokking AI Algorithms, Second Edition
A population-based algorithmic technique that iteratively improves candidate solutions through variation and selection inspired by biological evolution.
- How it is used
- Uses evolutionary algorithms to search large optimization spaces with many valid solutions and potential local optima.
- How deep it goes
- Explains population search, reproduction, mutation, and selection, then identifies encoding and crossover as further techniques.
- Examples
- Uses peppered moth adaptation and a weight-constrained knapsack to illustrate selection and optimization.
- What you can do after
- Apply evolutionary algorithms to optimization problems in other domain contexts.
Read how Grokking AI Algorithms, Second Edition explains evolutionary computation →
Also covered in
- Classic Computer Science Problems in Swift: Essential techniques for practicing programmers
- Advanced Algorithms and Data Structures
What to know first
- genetic algorithmA 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.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- crossoverCrossover is an evolutionary recombination technique that combines material from parent candidate solutions to produce one or more offspring.
- mutationMutation is a change to an existing entity, such as a value, state, data structure, or candidate representation.
Related concepts
- genetic algorithmincludes · 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.
- evolutionuses · Evolution is the cumulative change in the characteristics, structure, or behavior of a population or system across successive generations or states.
- artificial intelligencekind of · Artificial intelligence is the field of computing concerned with creating systems that perform tasks associated with intelligence, such as learning, reasoning, perception, and decision-making.
- binary-coded genetic algorithmincludes · A binary-coded genetic algorithm is a genetic algorithm whose candidate solutions use binary encoding.
- biology-inspired algorithmkind of · A biology-inspired algorithm is a computational method whose design models behaviors or processes observed in living organisms.
Questions about evolutionary computation
What is evolutionary computation?
Evolutionary computation is a family of search and optimization methods that iteratively improve candidate solutions through variation and selection inspired by biological evolution.
Which Manning books explain evolutionary computation?
Evolutionary Deep Learning: Genetic algorithms and neural networks, Optimization Algorithms: AI techniques for design, planning, and control problems, Self-Improving Agents and Grokking AI Algorithms, Second Edition.
What should I know before learning evolutionary computation?
Manning books that teach evolutionary computation usually introduce genetic algorithm, language model, crossover and mutation first.
What kinds of evolutionary computation are there?
Kinds of evolutionary computation include genetic algorithm and binary-coded genetic algorithm.
What is evolutionary computation a kind of?
Evolutionary computation is a kind of artificial intelligence. Artificial intelligence is the field of computing concerned with creating systems that perform tasks associated with intelligence, such as learning, reasoning, perception, and decision-making.
What is evolutionary computation also called?
Evolutionary computation is also called evolutionary algorithm.
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.



