The implementation of evolvable-substrate HyperNEAT algorithm in GO language. ES-HyperNEAT is an extension of the original HyperNEAT method for evolving large-scale artificial neural networks.
Omelianenko, Iaroslav. Applying Deep Machine Learning for Psycho-Demographic Profiling of Internet Users Using O.C.E.A.N. Model of Personality.arXiv [Cs.LG], 2017. P. 1β24. DOI: https://doi.org/10.48550/arxiv.1703.06914.
Omelianenko, Iaroslav. Applying Advanced Machine Learning Models to Classify Electro-Physiological Activity of Human Brain for Use in Biometric Identification.arXiv [Cs.LG], 2017. P. 1β8. DOI: 10.48550/arxiv.1708.01167
Omelianenko, I. Creation of Autonomous Artificial Intelligent Agents using Novelty Search method of fitness function optimization.Hal.science, 2018. P. 1β7. URL: https://hal.science/hal-01868756
Omelianeko, I. Simulation of the autonomous maze navigation using the NEAT algorithm.Problems in programming, 2023. Vol. 4, P. 76β89. DOI: 10.15407/pp2023.04.076
Omelianenko, I. and Sinitsyn, I. Artificial swarm intelligence.International Scientific Technical Journal "Problems of Control and Informatics", 2024, Vol. 69. N 3. P. 91β103. DOI: 10.34229/1028-0979-2024-3-7
changing the maximal_depth parameter in retina/es_hyper.neat.yml away from 3 to 5 for example will freeze within a few generations, and usually causing a killed signal sent to the program. This is pretty important since, in the es-HyperNEAT paper, the researchers set the maximal_depth to 32x32 for the retina experiment to reflect the complexity of the problem.