AI Christmas music

by Made by AI
 

Scientists have trained an AI system to write its own catchy Christmas songs by teaching it existing festive tunes. The system came up with catchy tunes with names like 'Syllabub Chocolatebell, 'Peaches Twinkleleaves' and 'Cocoa Jollyfluff' (stock image)

HOW DID THE TEAM TRAIN THEIR NEURAL NETWORK TO IMITATE ITS OWN CHRISTMAS SONGS?

The first step was to analyse the dataset by going through the existing tunes and storing the notes, chords and the sequences that were used in each tune. 
They used a long short-term memory network (LSTM).
The training consists of modelling the LSTM network that would 'learn' these sequences of notes and chords, with the goal of being able to generate its own sequences when fully learned. 
The training took approximately 3 hours with the Graphics Processing Unit  instance, used for deep learning purposes. 
This was by any means more computation than needed, but we knew we had little time and could run into the need to optimise hyperparameters in the model, which we also did with trying out different batch sizes on the model.