From 62ac53ac55f62b8fd6cf8caede0b08765327e780 Mon Sep 17 00:00:00 2001 From: metricsml-bot Date: Sun, 4 Aug 2024 08:25:56 +0000 Subject: [PATCH] Strip outputs from .ipynb files [skip ci] --- PM3/r_functional_approximation_by_nn_and_rf.Rmd | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/PM3/r_functional_approximation_by_nn_and_rf.Rmd b/PM3/r_functional_approximation_by_nn_and_rf.Rmd index aca4a796..0ac5583a 100644 --- a/PM3/r_functional_approximation_by_nn_and_rf.Rmd +++ b/PM3/r_functional_approximation_by_nn_and_rf.Rmd @@ -25,7 +25,7 @@ library(gbm) library(keras) ``` -# Functional Approximation by a Tree +# Function Approximation by a Tree We play around with the penalty level $cp$ below to illustrate how it affects the complexity of tree. Recall we may use this to prune the tree to improve predictive performance and lessen the noise in our final estimate. A simple penalty would be the number of leaves times a penalty level $\alpha$.