Musically Embodied Machine Learning (2025)

Welcome to Musically Embodied Machine Learning (2025)

Description: 

What are the creative possibilities of machine learning when embedded within musical instruments? If an instrument can learn and adapt with its player, how might this change musical practices? How do we adapt ML technology so that it can learn in-situ within an instrument? How do we design simplified interfaces to machine learning that become part of a musical instrument? These are the sorts of questions being explored by the Musically Embodied Machine Learning project. We’ll be bringing our new embedded ML technology to AAU for a workshop, where you can learn about embedded musical ML hands-on by building new prototype musical instruments. 

The workshop will take place in CreaTech Lab (CTL) and the Augmented Performance Lab (APL)

Schedule: 

Day 1: 

08:30 Coffee (APL)

09:00 Welcome / Short presentations

10:30 Lecture: MEML (Chris Kiefer)

12:00 Lunch

13:00 Lecture: Introduction to MEML Environment on Pi Pico (CTL)

Warn-up practical tasks

16-17:00ish Finish

Day 2: 

08:30 Coffee (APL)

09:00 Guest Lecture

10:30 Start of practical work - ideation session (CTL)

12:00 Lunch

13:00 Practical work

16-17:00ish Finish

Day 3: 

08:30 Coffee (APL)

09:00 Guest Lecture

14:00  Group sharing / presentation

15:00 Discussion / reflection: World Cafe exercise

17:00ish Close

Evening: Dinner and  informal performances (details TBC)

Prerequisites: 

We’ll try and accommodate a mixture of people with varied musical and technical skills. Work is in small groups. As long as skills balance out in the groups, participants will need at least one of these skills: 

- Basic electronics / coding 

- Musical instrument design (software and/or hardware) 

- Musical performance

Learning objectives: 

Understand the motivations behind the need for in-situ learning within hybrid and digital musical instruments 

Understand the musically creative possibilities of embedded machine learning 

Understand techniques and technologies for embedded machine learning 

Develop musical prototypes for interacting with embedded machine learning in instruments 

Experiment with advanced algorithms (such as extensions to reinforcement learning) that are specialised for in-situ machine learning 

Carry out musical instrument prototyping in small groups 

Perform with or demonstrate new musical prototypes

Key literature: TBA

Organizer: Daniel Overholt

Lecturers: Dr. Chris Kiefer, Andrea Martelloni & Daniel Overholt

ECTS: 3.0

Time: 15 - 17 January 2025

Place: Aalborg University (Room TBA)

Zip code: 2450

City: Copenhagen

Maximal number of participants: 20

Deadline: 2 January 2025

Important information concerning PhD courses: 

There is a no-show fee of DKK 3,000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before the start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately four months before start of the course.

We cannot ensure any seats before the deadline for enrolment, all participants will be informed after the deadline, approximately 3 weeks before the start of the course. 

For inquiries regarding registration, cancellation or waiting list, please contact the PhD administration at phdcourses@adm.aau.dk When contacting us please state the course title and course period. Thank you.