Skip to content

Commit

Permalink
remove duplicated lines
Browse files Browse the repository at this point in the history
  • Loading branch information
lcontento committed Jun 24, 2024
1 parent d0de94b commit 75ee6c5
Showing 1 changed file with 0 additions and 13 deletions.
13 changes: 0 additions & 13 deletions 03_MeNets.jl
Original file line number Diff line number Diff line change
Expand Up @@ -76,19 +76,6 @@ plotgrid(pred_train)
pred_test = predict(model_me, testpop_me[1:12], coef(fpm_me); obstimes=0:0.01:1)
plotgrid(pred_test ; ylabel="Y (Test data)")

#=
When we generated the data, we sampled two parameter values for each Subject.
In this Mixed-effect neural network, we're using two random effects, so there is hope that
the model can perfectly capture this two-dimensional between-subject variability.
But, what if our model had fewer random effects than there are dimensions of subject outcome variability?
Exercise:
Modify the model_me to only use a single random effect (change the I(2) in the
random effects and the number of inputs in the MLP) and see how the resulting
fit does.
=#


############################################################################################
############################################################################################
Expand Down

0 comments on commit 75ee6c5

Please sign in to comment.