High Precision in Frequency Domain for Deep Learning on Electronic Music

  • The frequency domain representations that have been used so far are inadequate for extracting the frequency patterns that are shorter than the detection window used. The new representation will enable multi-scale analysis of music, with higher amount of frequency data for higher frequencies.
  • The frequency domain representation provides a good solution for changing the problem of the scale-invariance of features (hard) to location-invariance of features (easy) in a machine learning model. Making models that provide location-invariance of features is achievable with currently popular models such as convolutional neural networks.

--

--

--

I am an applied mathematician and software engineer interested in electronic music generation using deep learning | http://akuz.me

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Paper Review:“Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation”

Constrained Bayesian Optimization — extended Bayesian optimization and its application in…

Use FastText on a Model Trained on GloVe

Simple Anomaly Detection algorithms for Streaming Data — Machine Learning

Predicting Cryptocurrency Prices with Machine Learning

How do you pick the right set of HyperParameters for a Machine Learning project ?

Parle and Gradient Descent for UI Layouts

M1 Mac Step Up Hugging Face Transformer

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Andrey Kuzmenko

Andrey Kuzmenko

I am an applied mathematician and software engineer interested in electronic music generation using deep learning | http://akuz.me

More from Medium

Steps of an End to end machine learning project | Part-1 | Business problem and Goal definition

How do FANG (now MANG)companies use Machine Learning (ML)?

What Is Machine Learning AntiFragility?

A Picture Shows You the Most Common Supervised Machine Learning Models