search

sferes2 / nn2

**Sferes2 module** generic toolbox for evolving neural networks
13 stars 9 forks source link

confusion around example_dnn_nsga2 configuration #7

Closed Antymon closed 4 years ago

Antymon commented 5 years ago

Hi,

In the mentioned example there are parameters controlling the number of neurons and connections set (such as min_nb_neurons etc). Unfortunately, after reading implementation I conclude they seem to have no impact under dnn::ff and control flow never uses them. Am I missing something here or is this just a mistake? If latter, same confusion is propagated through tests.

As a side question, are those parameters only meant for initialization ranges? That is, they don't really limit the number of neurons or connections through evolution if add/del rates are non-zero?

jbmouret commented 4 years ago

This is old (sorry), but for the record, min_nb_neurons, etc. are used only for initialization and not used in feed-forward mode (dnn:ff). They are not hard limits for evolution.