Recently came upon this algorithm for determining the key signature and mode of a given piece. It’s an interesting idea, looking at note frequencies, and I think I can apply this to produce more musical results. Currently working with music21 to preprocess my dataset again, determining what keys need to be represented. Stay tuned!
Just thought I’d write these down somewhere… Inspired by REMI and other projects, I think I’m going to consider a more chordal representation in the future. I’ve talked to a prominent piano player in the region, and I still think my model lacks musicality (can it even be musical? Even GPT-3 is not ‘language-cal’, it […]
I know it’s a bit late, but I’d just like to thank everyone who made this possible. Sebastian A. and Xander U. from 10th grade for getting me into this stuff, John Thickstun from the UW for giving me some ideas when I was starting out, Professor Sheng at the UW for giving me early […]
Check it out here!
A quick graph.
Having reached a decent stopping point with LSTMs (see previous post) I decided to implement attention myself and see if I could improve on the Music Transformer. I’d also heard about the OpenAI GPT-3 recently, and I wondered if I could borrow from their idea of a decoder-only Transformer. (GPT explanation) For reference, a feed […]
Basically, I wanted to do implement some kind of model myself. I decided on the LSTM (Long Short Term Memory.) It’s a bit early, and I don’t want to explain it all out, so I’ll just link a good explanation to LSTMs here. Implementation is easy: The main question is how to represent musical data […]
I started off this whole project by trying out an existing implementation of the Music Transformer. Transformers are based on attention, although a lot more complicated. Here’s a good guide. It was my first time working in depth with somebody else’s code, and it took some debugging to get it to work at all. However, […]
In this blog, I’m going to be mentioning attention a lot. So what is it? Let’s start with neural networks. A neural network is a program that learns from data, based loosely on a human brain. In this model, software neurons (functions) are grouped into layers, and they’re connected between the layers. The connections are […]