Unsupervised Machine Learning via FluCoMa In Max

Taught by: Ted Moore

- The Fluid Corpus Manipulation project (FluCoMa) provides novel machine learning tools for digital composition.

- Unsupervised Machine Learning refers to finding patterns in data.

- FluCoMa objects analyze audio to find similar/different sounds, plot complex analyses in 2D space, and organize sound slices.

- This provides a vast array of creative possibilities for composition, sound design, and performance.

- Ted Moore from FluCoMa will guide you through the creative possibilities of Unsupervised Learning with FluCoMa Max Package.

- Basic experience of FluCoMa is advised before joining the workshop.

For example, it is strongly recommended that you have taken the free on-demand workshop Using Machine Learning Creatively via FluCoMa In Max.

Level

What you'll learn

  • Find patterns in unorganized or unknown data
  • Plot data in 2 dimensional space (or other dimensions) by adjusting object parameters
  • Cluster sound slices to identify sounds that are similar and different from others
  • Gridify data points for interfacing with controllers

Course content

  • 1. Introduction
  • 2. Supervised vs Unsupervised Learning in Machine Learning
  • 3. Principle Component Analysis for Dimensionality Reduction in Sound Analysis
  • 4. Understanding the Uniform Manifold Approximation and Projection Algorithm
  • 5. The Importance of Scaling in Data Analysis
  • 6. Exploring KMeans Clustering in Audio Analysis
  • 7. Understanding the Jonker-Volgenant Algorithm (aka Grid)
  • 8. Exploring One-Dimensional Sound Organization with UMAP and MFCC Analysis
  • 9. Questions
  • Patches and Slides
Membership plan: Going Deeper | Topics: Sound Design ...

Access this course and 100s more for

From: £35 / month with a 7-day free trial

Subscribe
OR

Buy this course and own it forever

£ 15

Add to cart

Requirements

  • A computer and internet connection
  • Access to a copy of Max 8 (i.e. trial or full license)
  • Install of the free FluCoMa Max package

Who is this course for

  • Sound designers looking to implement unsupervised machine learning tools via FluCoMa in Max
  • Musicians looking to explore the creative possibilities offered with unsupervised machine learning tools via FluCoMa in Max

Useful links

About the workshop leader

Ted Moore (he / him) is a composer, improviser, and intermedia artist. He holds a PhD in Music Composition from the University of Chicago and recently served as a Research Fellow in Creative Coding at the University of Huddersfield, investigating the creative affordances of machine learning and data science algorithms as part of the FluCoMa project.​ His work focuses on fusing the sonic, visual, physical, and acoustic aspects of performance and sound, often through the integration of technology.

Music Hackspace
About Privacy