liveBook · Manning

Particle update operator

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

A particle update operator changes a particle's speed and position during an iteration of particle swarm optimization.

A particle update operator moves each particle during a particle swarm optimization iteration. It adjusts speed using the particle’s own best position and the swarm’s best position, then adds that speed to the current position. section 4.2.1

DEAP-style implementation

Register updateParticle with phi1=200 and phi2=200. During each generation, evaluate particles, refresh personal and global bests, and call toolbox.update(part, best).

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

How deep it goes
Implements random attraction, velocity limits, and position mutation, without deriving the optimization dynamics mathematically.
Examples
Uses a cannon-shot target-distance problem with velocity, angle, bounded speeds, and a 100-generation swarm.
What it assumes
Assumes particles contain positions, speeds, personal bests, and fitness values within a particle swarm optimization loop.
What you can do after
Apply it via DEAP’s toolbox to update a swarm after evaluating personal and global best particles.
How it connects
Connects particle position, velocity, personal best, global best, fitness evaluation, and particle swarm optimization.
Cover of Evolutionary Deep Learning: Genetic algorithms and neural networks
liveBookmanning.com
Read Evolutionary Deep Learning: Genetic algorithms and neural networks on liveBook Get the book at manning.com

Related concepts

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.