How to train a network with numeric feature vectors and a finite number of integer responses in the simplest manner?

I have coded a simple deep learning network in DLNetwork.m

The train and test numeric data are 2-d numeric vectors stored in the RRFsample .mat files in the variable names Xtrain and Xtest.

The response data are stored in Ytrain and Ytest in the RRF sample.mat file and are integers in the range 0,1,2,3,4,.

The trainNework function apparently requires categorical responses. The procedure for constructing these as described in "Train Networks with Numeric Featuers" seems very very convoluted.

Is there any simple way to make this code run? For example could I just convert the responses to five dimensional one hot vectors?

My goal is to construct a very simple example of a DL Network that can be used to teach the geometry and math to mathemtics students and mathematicians with no DL experience, but lots of math experience.

Thank you in advance for your advice and help.

MATLAB Version: 9.12.0.1975300 (R2022a) Update 3

LN