You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This map is a very useful resource for selecting the right tool for a problem at hand; also independent of scikit-learn. Why not including some machine learning references and tools outside of scitkit-learn?
For instance:
modules/packages compatible with the scikit-learn API such as
pystruct
seqlearn (already mentioned in the FAQ)
keywords for self-education such as:
neural networks
convolutional layer
recurrent networks
LSTM
non-scikit-learn tools such as
PyTorch
Tensorflow
Theano
What are your thoughts?
The text was updated successfully, but these errors were encountered:
The map is somewhat out of date, and I think contributions to update it are
welcome. But I don't think it wise to get into spaces of ML that
scikit-learn doesn't handle, but we could I suppose make clearer what kinds
problems you should go elsewhere for (although now that I say that it's a
very broad statement!)?
My understanding (see #2328) is that there is no interest in improving this scheme.
Also #18257 suggests to rework the tutorial in a comprehensive manner.
I'm closing this one: feel free to reopen if I'm wrong.
https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html
This map is a very useful resource for selecting the right tool for a problem at hand; also independent of scikit-learn. Why not including some machine learning references and tools outside of scitkit-learn?
For instance:
modules/packages compatible with the scikit-learn API such as
keywords for self-education such as:
non-scikit-learn tools such as
What are your thoughts?
The text was updated successfully, but these errors were encountered: