Evolving multimodal controllers with HyperNEAT

By Justin K. Pugh, Kenneth O. Stanley. 2013

25 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Mechanical Engineering, Robotics & Control, 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 Mechanical Engineering

In Robotics & Control

In Evolutionary Computation

Citations in the corpus

AutoML: A Survey of the State-of-the-Art (2019, background): “some studies [116, 117, 118, 25] describe the use of indirect encoding schemes to represent the network.”
Convolution by Evolution: Differentiable Pattern Producing Networks (2016, background): “…layers of a deeper neural network then there are two possibilities, either an extra input is given signaling which layer of weights the CPPN is outputting [19], or the CPPN is constrained to always have multiple output nodes, with a speciﬁc node outputting the weight for its assigned layer [21].”
Identifying Necessary Conditions for Open-Ended Evolution through the Artificial Life World of Chromaria (2014, methodology): “Recall also that each Chromarian contains two CPPNs : one to encode its neural network, and the other to encode its morphology.”
Gradient-free Policy Architecture Search and Adaptation (2017, background): “Most of them are based on biological genetics algorithms where there is a ﬁtness function that gets re-evaluated at each “generation” to determine whether “genotypes” are perturbed in the correct direction to evolve appropriately [12, 11, 19, 17].”
Large-Scale Evolution of Image Classifiers (2017, unknown): “…> . liest such “neuro-discovery” methods was neuro-evolution (Miller et al., 1989; Stanley & Miikkulainen, 2002; Stanley, 2007; Bayer et al., 2009; Stanley et al., 2009; Breuel & Shafait, 2010; Pugh & Stanley, 2013; Kim & Rigazio, 2015; Zaremba, 2015; Fernando et al., 2016; Morse & Stanley, 2016).”
Evolving Deep Convolutional Neural Networks for Image Classification (2017, background): “combined with the compositional pattern producing networks [29], was proposed to evolve a larger scale neural network with an indirect encoding strategy. Motivated by the HyperNEAT, multiple variants [30]–[32] were proposed to evolve even larger scale neural networks. However, the major deﬁciencies ”