Recap from Day 003
In day 003, we learned about Wekinator, the tool that allows musicians to use machine learning in their work without writing a single line of code. We also learned about Open Sound Control (OSC), the communication protocol used by Wekinator for sending and receiving data. Today I’ll present an overview of Wekinator.
Wekinator Overview
Wekinator receives inputs and processes them using mathematical functions. Do you still remember what those mathematical functions are called? You’re right. They’re called models. Those models produce output values from input data received by Wekinator.
Wekinator Overview
“Inputs could be sent from any real-time input, such as game controllers, webcam input, motion tracking, audio input, sensors connected to Arduino, etc. Outputs could be sent to any real-time process, such as music (Max/MSP, ChucK, PD, SuperCollider, Ableton/Max4Live…), animation (Processing, OpenFrameworks, …), games (Unity3D), robots or physical actuators (e.g. using Arduino), etc.” — Wekinator Instructions Wekinator builds models using supervised machine learning algorithms, instead of using a human writing code. “You create models by providing training examples of inputs and the outputs that should correspond to them. A learning algorithm builds a model from the training examples:” — Wekinator Instructions
For the type of things we would love to build as musicians, we’ll use a set of Supervised Learning algorithm.
Wekinator Overview
Wekinator Walkthrough
Below is a quick walkthrough from Wekinator’s website. Walkthrough Once you know what Wekinator does, let's do a quick walkthrough to get you started. 1. Download at least one of the…wekinator.org
Control a platformer game with voice commands using dynamic time warping:
You made it to the end of day 004. Thank you for taking time out of your schedule and allowing me to be your guide on this journey.