-
Notifications
You must be signed in to change notification settings - Fork 11
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
missing neuroevolution functions from docs #143
Comments
Awesome, thanks so much @shiffman! I plan to take a look at these starting next week and track questions/updates here |
Hi Moon @MOQN, maybe we could discuss whether we add neuroevolution to NN page, or have a dedicated page for it. Some ideas come to my mind:
OR OR |
@QuinnHe Thanks for addressing this! I am currently indecisive about whether to have a reference page or a page in the Learn section. Let's discuss it (and Gottfried's suggestion) in a webteam meeting? |
I don't feel strongly about this either way but I think it's ok to go with:
It's not clear to me whether people will use the neuroevolution features of ml5.js broadly or if it's a niche thing just for the nature of code book readers. So I think just documenting them and linking out to my materials is a fine way to start! And if we get a lot of questions or see a lot of neuroevolution projects maybe we build it out more? |
Sounds good!! On it, will have them ready before next regroup. Thanks Dan! |
Resolved by #154 . |
I'm opening an issue with info and resources about neuroevolution for the website documentation that @sharellb plans to work on! (I just sent an email but realized maybe it makes more sense to track here.)
I cover neuroevolution in Chapter 11 from Nature of Code. (Chapters 9 and 10 have the base material about genetic algorithms and neural network fundamentals).
The functions I added to ml5.neuralNetwork to make neuroevolution "easier" are
crossover()
andmutate()
. I think these are missing from the docs and there might be other elements also missing? I don't remember as I hacked all this together while writing the book under tight deadlines!There is also this discussion with @ziyuan-linn which may be relevant:
ml5js/ml5-next-gen#138
Finally, I highly recommend the work on David Ha for a deeper dive into neuroevolution!
The text was updated successfully, but these errors were encountered: