search

yaricom / goNEAT

The GOLang implementation of NeuroEvolution of Augmented Topologies (NEAT) method to evolve and train Artificial Neural Networks without error back propagation
MIT License
75 stars 19 forks source link

Missing genome file documentation #22

Closed rubens21 closed 3 years ago

rubens21 commented 3 years ago

hi @yaricom ,

I am trying to use this lib, but I did not find a documentation about how the genoma file is created. I could guess some columns meaning, but not all of them.

Could we have short description of each column?

Thank you

yaricom commented 3 years ago

Hello @rubens21,

The library now supports two formats of genome file: plain text and yaml. The former is a bit outdated right now, however it is more concise. While the YAML format is more self descriptive.

Please take a look at test_seed_genome.yml

Let me know if this helped you.

Thank you, Iaroslav

rubens21 commented 3 years ago

Thank @yaricom,

That file is much easier to understand. Are traits a NEAT thing or is it something particular to your project? Sorry, I am not familiar with NEAT yet. I just started to study it.

yaricom commented 3 years ago

Hello @rubens21,

The traits are the part of the NEAT algorithm. It is individual features of organisms which can mutate during the evolution. You can ignore it as for now as traits have no influence on reproduction.

Iaroslav

rubens21 commented 3 years ago

Thank you a lot for your answers and for publishing this project. I will continue to read about NEAT. :-)