Cartesian Genetic Programming

By Julian Francis Miller. 2015

1,126 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Evolutionary Computation

How researchers see this paper

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

In Artificial Intelligence

In Evolutionary Computation

Citations in the corpus

AutoML: A Survey of the State-of-the-Art (2019, methodology): “To represent variable-length network structures, Suganuma et al. [21] use Cartesian genetic programming (CGP) [101], [102] encoding scheme to represent the network as directed acyclic graphs, for the CNN architecture representation.”
Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels (2019, methodology): “Two example algorithms of this category are NeuroEvolution of Augmenting Topologies (NEAT) [1] and Cartesian Genetic Programming of Artificial Neural Networks (CGPANN) [2,3].”
A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification (2018, methodology): “CGP-CNN utilises Cartesian Genetic Programming (CGP) [11] because the ﬂexibility of CGP’s encoding scheme is suitable to eﬀectively encode the complex CNN architectures.”
SMASH: One-Shot Model Architecture Search through HyperNetworks (2017, methodology): “Additionally, although our method is not evolutionary, our encoding scheme is reminiscent of CGP [23].”
A genetic programming approach to designing convolutional neural network architectures (2017, methodology): “Moreover, to maintain a neutral drift, which is effective for CGP evolution [21, 22], we modify a parent by the neutral mutation if”
Evolution of Cartesian Genetic Programs for Development of Learning Neural Architecture (2011, methodology): “CGP was developed from the work of Miller and Thomson for the evolutionary design of feed-forward digital circuits (Miller et al., 1997; Miller and Thomson, 2000).”
Cartesian genetic programming encoded artificial neural networks: a comparison using three benchmarks (2013, background): “CGP [28, 30] is a form of GP in which computational structures are organised as directed, often acyclic graphs indexed by their Cartesian coordinates.”
In search of intelligence: evolving a developmental neuron capable of learning (2014, methodology): “The best chromosome is always promoted to the next generation; however, if two or more chromosomes achieve the same highest ﬁtness then newest (genetically) is always chosen (Miller et al., 2000).”
Global Optimization Algorithms -- Theory and Application (2009, methodology): “Electrical Engineering and Circuit Design [870, 113, 861, 871, 872, 868] Symbolic Regression and Function Synthesis [862, 863, 114, 863]”
Evolution of neural networks using Cartesian Genetic Programming (2010, methodology): “Cartesian Genetic Programming (CGP) is an Evolutionary Programming technique developed by Miller and Thomson [16].”
Developmental Plasticity in Cartesian Genetic Programming based Neural Networks (2016, methodology): “A plastic CGPANN (PCGPANN) is a developmental form of Cartesian Genetic Programming ANN algorithm.”