Questions tagged [neat]

For questions related to the neuroevolution technique called NeuroEvolution of Augmenting Topologies (NEAT), introduced in the paper "Evolving Neural Networks through Augmenting Topologies" (2002) by Kenneth O. Stanley and Risto Miikkulainen.

See the paper that introduced NEAT Evolving Neural Networks through Augmenting Topologies (2002) by Kenneth O. Stanley and Risto Miikkulainen. See also Efficient Reinforcement Learning Through Evolving Neural Network Topologies by the same authors.

Other possibly useful resources

74 questions
6
votes
0 answers

Speciation in NEAT - Advantages of keeping stable number of species

I found several methods for setting the compatibility distance in NEAT: some normalize it, some don't, some automatically adjust it. In a few tests I am running, using normalized static compatibility distance, the number of species increase very…
kuma
  • 341
  • 1
  • 10
4
votes
1 answer

Can a crossover result in a node with no outgoing connections?

I'm currently implementing the original NEAT algorithm in Swift. Looking at figure 4 in Stanley's original paper, it seems to me there is a chance that node 5 will have no (enabled) outgoing connection if parent 1 is assumed the fittest parent and…
Daniël
  • 43
  • 4
4
votes
3 answers

How do you implement NEAT by taking into account the loops?

I'm working on my own implementation of NEAT algorithm based on the original 2002 paper called "Efficient Reinforcement Learning through Evolving Neural Network Topologies" (by Kenneth O. Stanley and Risto Miikkulainen). The way the algorithm is…
Emad
  • 183
  • 1
  • 10
1
vote
0 answers

NEAT Speciation distance: How does one treat disabled connections?

When calculating the distance between two genomes, how does one treat disabled connections? For example, consider the following genome: [1, 0.2, E] [2, 0.1, D] [3, 0.2, E] [4, 0.15, E] [5, 0.3, D] [7, 0.25, D] [8, 0.25, E] [9, 0.1,…
Brent Parker
  • 111
  • 2
0
votes
0 answers

Does the NEAT alogrithm disable genes randomly?

It is not mentioned in the original paper, if genes can be disabled randomly. They only mention that the connection gene is disabled, when a node is inserted in it's place. Is it the case, that genes can be disabled randomly as well?
Servus
  • 101