Gene

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

A gene is a heritable unit of biological information that influences an organism's traits and occupies a position on a chromosome.

A gene is a heritable unit of biological information that influences an organism’s traits. Biologically, it is a DNA sequence located on a chromosome; in genetic algorithms, it encodes one or more traits of an individual. section 2.4.3 section 2.5.1

DNA contains ordered base pairs, folds into chromosomes, and includes many genes. A gene may contain hundreds or thousands of base pairs, while a chromosome may contain hundreds or thousands of genes. Genetic algorithms simplify this biology by working mainly with genes and chromosomes and by mimicking selected aspects of meiosis. section 2.5.1

In a genetic algorithm, a gene can be represented in several practical ways:

• A Boolean or numeric value, such as 0 or 1, occupying one position in a chromosome. section 2.5.2
• An array value or a group of values, depending on how much information one trait requires. section 2.5.2
• A structured subgroup representing an object, such as a polygon defined by points, color, and transparency. section 3.5

Genes as a NumPy population

A simple population can contain 100 individuals, each represented by 100 binary genes: pop = np.random.randint(0, 2, size=(population, genes)). Each row is one chromosome and each position is a gene. In the EvoLisa example, groups of ten floating-point values instead encode polygon geometry, color, and alpha, which are extracted and rendered before fitness evaluation. section 2.5.3 section 3.5

Figure 2.7 DNA, genes, chromosomes, a nucleus, and a cell

Use the diagram to trace the relationship between DNA, genes, chromosomes, the nucleus, and the cell. section 2.5.1

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

How deep it goes

Defines genes biologically and computationally, then demonstrates representations, but stops short of detailed molecular genetics.

Examples

Uses binary NumPy chromosomes and EvoLisa polygon genes containing coordinates, color, and transparency.

What it assumes

Assumes basic familiarity with traits and arrays while introducing DNA, chromosomes, genes, and simplified meiosis at a high level.

What you can do after

Apply genes by encoding traits as binary values, numeric arrays, or structured value groups for evolutionary optimization.

How it connects

Links genes with DNA, chromosomes, traits, meiosis, genetic algorithms, individuals, and fitness.

liveBookmanning.com

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

Also explained in

• 

  liveBookmanning.com
  Advanced Algorithms and Data StructuresA gene is an individual position in a genetic-algorithm chromosome that represents one optimization variable and its assigned value.
• 

  liveBookmanning.com
  Classic Computer Science Problems in Swift: Essential techniques for practicing programmersGene is a book-specific array-based representation of a nucleotide sequence as an ordered collection of codons.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionA gene is an individual value or position within an evolutionary algorithm chromosome that contributes to the encoded candidate solution.
• 

  liveBookmanning.com
  Optimization Algorithms: AI techniques for design, planning, and control problemsA gene is a segment of genetic material that encodes a specific biological property or functional product.

Compare how 5 books explain gene →

Related concepts

• chromosomepart of · A chromosome is an encoded representation of a candidate solution in an evolutionary algorithm, composed of genes or other solution components.
• individualpart of · An individual is a single candidate solution represented as a member of an evolutionary algorithm's population and evaluated by its fitness.
• genetic algorithmused by · 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.

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.