Professor: Philippe Esling
Lessons • Setup • Detailed lessons • Contribution • About
This repository contains the courses in creative machine learning applied to music and other creative mediums and how to develop and use these models inside MaxMSP and Ableton Live. This course is given at the MaxMSP summer school ((Tokyo university of the arts, Japan)). The courses slides along with a set of MaxMSP patches, Max4Live devices and interactive Jupyter Notebooks will be updated along the course to provide all the examples. This course is proudly provided by the ACIDS group, part of the Analysis / Synthesis team at IRCAM. This course can be followed entirely online through the set of Google slides and Colab notebooks links provided openly along each lesson. However, we do recommend to fork the entire environment and follow the interactive notebooks through Jupyter lab to develop your own coding environment.
This course is meant to be only an introduction to all of these complex ideas. We highly recommend to follow the companion "Creative Machine Learning" course to truly acheive mastery of deep models development.
Table of Contents
Quick explanation. For each of the following lessons, you will find a set of badges containing links to different parts of the course, which allows you to follow either the online or offline versions.
- Online:
- Offline:
Simply click on the corresponding badge to follow the lesson. Note that if the badge is displayed in red color as follows
This course provides a brief history of the development of artificial intelligence and introduces the general concepts of machine learning through a series of recent applications in the creative fields. This course also presents the pre-requisites, course specificities, toolboxes and tutorials that will be covered and how to setup the overall environment. Finally, we introduce the formal notions required to understand machine learning along with classic problems of linear models for regression and classification. We discuss the mathematical derivation for optimization and various problems of overfitting, cross-validation and model properties and complexity that are still quintessential in modern machine learning. We finish with a quick roundup of how to use existing deep models on GitHub.
This course provides a brief history of the development of neural networks along with all mathematical and implementation details. We discuss geometric perspectives on neurons and gradient descent and how these interpretation naturally extend to the case of multi-layer perceptrons. We further introduce more advanced types of neural networks such as convolutional and recurrent architectures, along with more advanced models (LSTM, GRU) and recent developments such as residual architectures. We further discuss issues of regularization and initialization in networks. Finally, we finish this course by discussing the recent attention mechanism and transformer architectures and provide a set of modern applications.
In this course, we will discuss how to embed existing deep models into MaxMSP. In order to capitalize on existing body of work in ML research, we will seek to run the model from Python (as most research is being done in this language). Hence, we will first discuss OSC communication and how to setup an OSC protocol and exchange between MaxMSP and Python. We briefly introduce the basics of Max4Live devices and show how to use these through the case study of the FlowSynth AI-based synthesizer control.
In this course, we go further in how we can potentially embed existing deep models into MaxMSP. One of the key problem of the previous method (OSC and Python) resides in the lack of computational efficiency. Hence, we seek here to learn how to develop our own externals. We provide an introduction to the Max SDK in order to develop our own externals in C. We further discuss the Torchscript and Tensorflow Lite interfaces that allow to embed Python models into efficient C codes. We show how to use these skills through the case study of the RAVE real-time deep audio generation.
Along the tutorials, we provide a reference code for each section. This code contains helper functions that will alleviate you from the burden of data import and other sideline implementations. You will find designated spaces in each file to develop your solutions. The code is in Python (notebooks impending) and relies on the concept of code sections, which allows you to evaluate only part of the code (to avoid running long import tasks multiple times and concentrate on the question at hand.
Please refer to the setup notebook to check if your configuration is correct
In order to get the baseline scripts and notebooks to work, you need to have a working distribution of Python 3.7 as a minimum (we also recommend to update your version to Python 3.9). We will also be using a large set of libraries, with the following ones being the most prohiminent
We highly recommend that you install Pip or Anaconda that will manage the automatic installation of those Python libraries (along with their dependencies). If you are using Pip, you can use the following commands
pip install -r requirements.txt
If you prefer to install all the libraries by hand to check their version, you can use individual commands
pip install numpy
pip install scikit-learn
pip install torch
pip install jax
pip install librosa
pip install matplotlib
For those of you who have never coded in Python, here are a few interesting resources to get started.
In order to ease following the exercises along with the course, we will be relying on Jupyter Notebooks. If you have never used a notebook before, we recommend that you look at their website to understand the concept. Here we also provide the instructions to install Jupyter Lab which is a more integrative version of notebooks. You can install it on your computer as follows (if you use pip)
pip install jupyterlab
Then, once installed, you can go to the folder where you cloned this repository, and type in
jupyter lab
Please take a look at our contributing guidelines if you're interested in helping!
Code and documentation copyright 2012-2023 by all members of ACIDS.
Code released under the CC-BY-NC-SA 4.0 licence.