A Reductionist Approach To The Analysis Of Learning
Biol Cybern (2014) 108:183–201
DOI 10.1007/s00422-014-0589-3
ORIGINAL PAPER
A reductionist approach to the analysis of learning in brain–computer interfaces
Zachary Danziger
Received: 14 January 2013 / Accepted: 28 January 2014 / Published online: 15 February 2014
© Springer-Verlag Berlin Heidelberg 2014
Abstract The complexity and scale of brain–computer interface (BCI) studies limit our ability to investigate how humans learn to use BCI systems. It also limits our capacity to develop adaptive algorithms needed to assist users with their control. Adaptive algorithm development is forced offline and typically uses static data sets. But this is a poor substitute for the online, dynamic environment where algorithms are ultimately deployed and interact with an adapting user.
This work evaluates a paradigm that simulates the control problem faced by human subjects when controlling a BCI, but which avoids the many complications associated with full-scale BCI studies. Biological learners can be studied in a reductionist way as they solve BCI-like control problems, and machine learning algorithms can be developed and tested in closed loop with the subjects before being translated to full
BCIs. The method is to map 19 joint angles of the hand (representing neural signals) to the position of a 2D cursor which must be piloted to displayed targets (a typical BCI task).
An investigation is presented on how closely the joint angle method emulates BCI systems; a novel learning algorithm is evaluated, and a performance difference between genders is discussed. Keywords Brain–computer interface · Machine learning ·
Motor learning · Cyberglove
Z. Danziger (B)
Fitzpatrick Center for Interdisciplinary Engineering,
Medicine and Applied Sciences (CIEMAS), Duke University,
100 & 101 Science Drive, Campus Box 90281, Durham,
NC 27710, USA e-mail: zd10@duke.edu
1 Introduction
The promise of brain–computer interfaces (BCIs) is to provide a human user with non-muscular control over an
DOI 10.1007/s00422-014-0589-3
ORIGINAL PAPER
A reductionist approach to the analysis of learning in brain–computer interfaces
Zachary Danziger
Received: 14 January 2013 / Accepted: 28 January 2014 / Published online: 15 February 2014
© Springer-Verlag Berlin Heidelberg 2014
Abstract The complexity and scale of brain–computer interface (BCI) studies limit our ability to investigate how humans learn to use BCI systems. It also limits our capacity to develop adaptive algorithms needed to assist users with their control. Adaptive algorithm development is forced offline and typically uses static data sets. But this is a poor substitute for the online, dynamic environment where algorithms are ultimately deployed and interact with an adapting user.
This work evaluates a paradigm that simulates the control problem faced by human subjects when controlling a BCI, but which avoids the many complications associated with full-scale BCI studies. Biological learners can be studied in a reductionist way as they solve BCI-like control problems, and machine learning algorithms can be developed and tested in closed loop with the subjects before being translated to full
BCIs. The method is to map 19 joint angles of the hand (representing neural signals) to the position of a 2D cursor which must be piloted to displayed targets (a typical BCI task).
An investigation is presented on how closely the joint angle method emulates BCI systems; a novel learning algorithm is evaluated, and a performance difference between genders is discussed. Keywords Brain–computer interface · Machine learning ·
Motor learning · Cyberglove
Z. Danziger (B)
Fitzpatrick Center for Interdisciplinary Engineering,
Medicine and Applied Sciences (CIEMAS), Duke University,
100 & 101 Science Drive, Campus Box 90281, Durham,
NC 27710, USA e-mail: zd10@duke.edu
1 Introduction
The promise of brain–computer interfaces (BCIs) is to provide a human user with non-muscular control over an