Multilayer perceptron: load the model from model/model.json
Run the classifier
The model takes a Latin string as an input.
Parse the string with the script provided in parser.js
Use the embedder (cf. 2) to encode the parsed string into an array
Split the array into chunks of 16 items each (array.length = 16)
Feed each array to the multilayer perceptron (cf. 3).
The output will be an array of length 2. Apply the softmax function to this output. The first element of the softmaxed array will be the Ciceronianity score.
