- author = "Vladimir Stanovov and Shakhnaz Akhmedova and Eugene Semenkin",
- title = "Difference-Based Mutation Operation for Neuroevolution of Augmented Topologies",
- journal = "Algorithms",
- year = "2021",
- volume = "14",
- number = "5",
- pages = "127",
- keywords = "genetic algorithms, genetic programming, NEAT, ANN, neuroevolution, classification, inverted pendulum",
- ISSN = "1999-4893",
-
URL = "
https://www.mdpi.com/1999-4893/14/5/127",
-
DOI = "
doi:10.3390/a14050127",
- size = "18 pages",
- abstract = "a search operation is proposed for the neuroevolution of augmented topologies, namely the difference-based mutation. This operator uses the differences between individuals in the population to perform more efficient search for optimal weights and structure of the model. The difference is determined according to the innovation numbers assigned to each node and connection, allowing tracking the changes. The implemented neuroevolution algorithm allows backward connections and loops in the topology, and uses a set of mutation operators, including connections merging and deletion. The algorithm is tested on a set of classification problems and the rotary inverted pendulum control problem. The comparison is performed between the basic approach and modified versions. The sensitivity to parameter values is examined. The experimental results prove that the newly developed operator delivers significant improvements to the classification quality in several cases, and allow finding better control algorithms.",
-
notes = "also known as \cite{a14050127}
Institute of Informatics and Telecommunication, Reshetnev Siberian State University of Science and Technology, 660037 Krasnoyarsk, Russia
This paper is the extended version of our published in IOP Conference Series: Materials Science and Engineering, Krasnoyarsk, Russia, 15 February 2021.",
