After understanding the basics of deep learning, it's time to apply the skills acquired to a practical case. We've seen in the previous section that two libraries we know are listed in packages available in R for DNNs section. I refer to the nnet
and neuralnet
packages that we learned to use in the previous chapters through practical examples. Since we have some practice with the neuralnet
library, I think we should start our practical exploration of the amazing world of deep learning from here.
To start, we introduce the dataset we will use to build and train the network. It is named the College
dataset, and it contains statistics for a large number of US colleges, collected from the 1995 issue of US News and World Report. This dataset was taken from the StatLib
library, which is maintained at Carnegie Mellon University, and was used in the ASA Section on Statistical Graphics.
Things for us are further simplified because we do not have to retrieve...