The Microbial Genetic Algorithm

By Inman R. Harvey. 2009

156 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Convolution by Evolution: Differentiable Pattern Producing Networks (2016, methodology): “The simpler evolutionary algorithm is the microbial genetic algo-rithm (mGA) [8] with a population size of 50.”
PathNet: Evolution Channels Gradient Descent in Super Neural Networks (2017, neutral): “This is a binary tournament selection algorithm ( B = 2) [7].”
The 2014 General Video Game Playing Competition (2016, unknown): “2) 12th—Sample GA: The Sample GA controller is a rolling horizon open loop implementation of a minimalistic steady state genetic algorithm, known as a microbial GA [28].”
Evolvable Neuronal Paths: A Novel Basis for Information and Search in the Brain (2011, methodology): “The Results section compares the performance of PEA with various parameter settings against the equivalent standard gene based microbial genetic algorithm [9] on various combinatorial and real-value optimization problems, and for evolution in variable environments.”
DeepType: Multilingual Entity Linking by Neural Type System Evolution (2018, background): “Genetic Algorithm The best subset of type axes can be found by representing type axes as genes carried by Npopulation individuals in a population undergoing mutations and crossovers (Harvey 2009) over G generations.”
Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts (2021, methodology): “Moreover, while [9] uses a simple binary-tournament genetic algorithm [18], we opt for a modern state-of-the-art evolution strategy algorithm, PGPE [45] with ClipUp [50], performing well enough to produce interesting results within a few thousand computational steps.”
Generative Art Using Neural Visual Grammars and Dual Encoders (2021, methodology): “A parallel asynchronous binary tournament selection algorithm is used to evolve the images [19].”
Transfer Learning in Deep Reinforcement Learning: A Survey (2020, methodology): “The population of pathway is evolved using a tournament selection genetic algorithm [124].”