• Publications
  • Influence
Human model evaluation in interactive supervised learning
TLDR
Model evaluation plays a special role in interactive machine learning systems in which users rely on their assessment of a model's performance in order to determine how to improve it. Expand
A Meta-Instrument for Interactive, On-the-Fly Machine Learning
TLDR
We propose a method for harnessing machine learning algorithms within a radically interactive paradigm, in which the designer may repeatedly generate examples, train a learner, evaluate outcomes, and modify parameters in a single software environment. Expand
Towards a dimension space for musical devices
TLDR
The authors propose a dimension space representation that can be adapted for visually displaying musical devices, revealing its usefulness in exposing patterns across existing musical devices and aiding in the design of new ones. Expand
Real-time human interaction with supervised learning algorithms for music composition and performance
TLDR
This thesis examines machine learning through the lens of human-computer interaction in order to address fundamental questions surrounding the application of machine learning to real-life problems. Expand
Don't forget the laptop: using native input capabilities for expressive musical control
TLDR
We draw on our experiences with the Princeton Laptop Orchestra to discuss novel uses of the laptop's native physical inputs for flexible and expressive control. Expand
Using Interactive Machine Learning to Support Interface Development Through Workshops with Disabled People
TLDR
We applied interactive machine learning (IML) to the creation and customisation of gesturally controlled musical interfaces in six workshops with people with learning and physical disabilities. Expand
ACE: A Framework for Optimizing Music Classification
TLDR
This paper presents ACE (Autonomous Classification Engine), a framework for using and optimizing classifiers. Expand
Grab-and-Play Mapping: Creative Machine Learning Approaches for Musical Inclusion and Exploration
TLDR
We present the first implementation of a new tool for prototyping digital musical instruments, which allows a user to literally grab a controller and turn it into a new, playable musical instrument almost instantaneously. Expand
Human-Centred Machine Learning
TLDR
A human-centered approach to machine learning that rethinks algorithms and interfaces to algorithms in terms of human goals, contexts, and ways of working can make machine learning more useful and usable. Expand
A Demonstration of Bow Articulation Recognition with Wekinator and K-Bow
TLDR
Wekinator allows a musician user to rapidly build customized bow gesture models from scratch by demonstrating bowing gestures to form a training set; the user can also interactively refine these models through iterative changes to both the learning algorithms and dataset. Expand
...
1
2
3
4
5
...