Creating Playlists with Artificial Intelligence
ISEF · 2019 Robotics and Intelligent Machines
Overview
It has never been easier to listen to one's favourite music than today: With services like Spotify or Apple Music, we have access to an almost unlimited number of songs. But this variety can be overwhelming sometimes. The goal of my project was the creation of an artificial intelligence which is able to generate playlists based on a given song. I used the so-called neural networks which are widely used in domains such as object or speech recognition. 2000 playlists of Spotify (for example "Pop Rising" or "Summer Acoustic") were used as examples to train the neural networks. I developed novel methods for Training (including a novel loss function and a unique combination of several networks) and was able to achieve a significant increase in performance compared to other methods.
Competition history
- ISEF 2019
Resources
Related projects
ISEF · 2019
Auto Arranger Based on Deep Learning Methods
ISEF · 2019
ExploreYourMind: Software for Harmonic Combination of Video and Music
ISEF · 2017
Android Application Development for Algorithmic Music Generation through Artificial Neural Networking
ISEF · 2021
Efficient Music Genre Classification with Deep Convolutional Neural Networks
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair