Models documentation header mismatch

[marcelglueck]

The problem

It seems that the header for quite some neural network models does not fit their content:

Example:

• https://parsnip.tidymodels.org//reference/details_mlp_keras.html: Header says "Multilayer perceptron", but the document says otherwise ("keras_mlp() fits a single layer...")

The same applies to https://parsnip.tidymodels.org//reference/details_mlp_nnet.html. Please correct me if I am wrong.

[topepo]

This isn't necessary. Historically, the input layer is counted. An MLP is a neural network with at least one layer of hidden units. For example, long ago, logistic regression was considered a single-layer perceptron.

We could amend the documentation to say a "single layer of hidden units" if that makes it less confusing.

[marcelglueck]

Thanks for clarifying. Not sure whether the amendment makes it less confusing. Might be just me not being a ML guy. 😅

[github-actions]

This issue has been automatically locked. If you believe you have found a related problem, please file a new issue (with a reprex: https://reprex.tidyverse.org) and link to this issue.