Evolution
Evolution is the cumulative change in the characteristics, structure, or behavior of a population or system across successive generations or states.
Evolutionary Deep Learning: Genetic algorithms and neural networks
Biological evolution is the change in heritable characteristics of populations across generations through processes such as variation and selection.
- How it is used
- Uses evolutionary mechanisms to optimize processes, parameters, structures, and machine-learning systems through population-based search.
- How deep it goes
- Implements simplified life simulations with fitness, selection, inheritance, mutation, plotting, and parameter experiments rather than biological genetic detail.
- Examples
- Demonstrates cell populations, inherited traits, fitness equations, mutation rules, live plots, and notebook exercises that vary evolutionary operators.
- What you can do after
- Build it from scratch as a Python life simulation, then modify fitness functions, inheritance, selection, mutation, and monitoring parameters.
Read how Evolutionary Deep Learning: Genetic algorithms and neural networks explains evolution →
Architecture Modernization: Socio-technical alignment of software, strategy, and structure
Evolution is the progression of a component from novel and uncertain origins toward increasingly industrialized, stable, and efficient forms.
- How it is used
- Guides Wardley Mapping toward future scenarios by examining how components change rather than treating the current landscape as fixed.
- How deep it goes
- Explains an evolution spectrum and a collaborative assessment process, while leaving placement partly subjective and requiring further research.
- Examples
- Uses smartphone cameras, evolution criteria, breakout discussions, and a visual mapping template as concrete learning artifacts.
- What you can do after
- Evaluate component positions, challenge maps through discussion, and anticipate changes driven by demand, competition, and external events.
Grokking AI Algorithms, Second Edition
Evolution is the cumulative change in inherited characteristics of populations across generations through variation and differential survival or reproduction.
- How it is used
- Explains how inherited variation and differential survival produce adaptation across generations.
- How deep it goes
- Explains variation, mutation, branching populations, and selection through intuition and examples, stopping short of detailed biology.
- Examples
- Uses branching human evolution, peppered moth coloration, and reproduction with mutation to illustrate evolutionary change.
- What you can do after
- Evaluate/understand how populations change through inherited variation and environmental selection.
Read how Grokking AI Algorithms, Second Edition explains evolution →
Related concepts
- evolutionary computationused by · Evolutionary computation is a family of search and optimization methods that iteratively improve candidate solutions through variation and selection inspired by biological evolution.
- natural selectionproduced by · Natural selection is the evolutionary process by which heritable traits affecting survival or reproduction influence which variants become more common in a population.
- Wardley Mappingused by · Wardley Mapping is a visual strategy technique that maps user needs and supporting components in a value chain and positions them by evolutionary maturity.
- acceleratorproduced by · An accelerator is an action intended to speed the evolution of one or more components in a strategic landscape.
- model architectureused by · The structural organization of a computational system’s components, relationships, and operations that determines how it processes information or behaves.
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.