✳flâneur — a map of the web's best reading

3 NeuroEvolution of Augmenting Topologies (NEAT)

cs.cmu.edu · 2,039 words · saved by 1 readers

The NEAT method of evolving artificial neural networks combines the usual search for appropriate network weights with complexification of the network structure. This approach is highly effective, as shown e.g. in comparison to other neuroevolution (NE) methods in the double pole balancing benchmark task . The NEAT method consists of solutions to three fundamental challenges in evolving neural network topology: (1) What kind of genetic representation would allow disparate topologies to crossover in a meaningful way? Our solution is to use historical markings to line up genes with the same origin. (2) How can topological innovation that needs a few generations to optimize be protected so that it does not disappear from the population prematurely? Our solution is to separate each innovation into a different species. (3) How can topologies be minimized throughout evolution so the most efficient solutions will be discovered? Our solution is to start from a minimal structure and add nodes an

3 NeuroEvolution of Augmenting Topologies (NEAT) Next: 4 The Robot Duel Up: Competitive Coevolution through Evolutionary Previous: 2 Background Subsections 3.1 Genetic Encoding 3.2 Tracking Genes through Historical Markings 3.3 Protecting Innovation through Speciation 3.4 Minimizing Dimensionality through Complexification 3 NeuroEvolution of Augmenting Topologies (NEAT) The NEAT method of evolving artificial neural networks combines the usual search for appropriate network weights with complexification of the network structure. This approach is highly effective, as shown e.g. in comparison to

Explore this link on the map →

related reading