Learning algorithms for human-machine interfaces

Zachary Danziger*, Alon Fishbach, Ferdinando A. Mussa-Ivaldi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

37 Scopus citations


The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The highdimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore-Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction.

Original languageEnglish (US)
Article number4776455
Pages (from-to)1502-1511
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Issue number5
StatePublished - May 2009


  • Adaptive learning
  • Hand posture
  • Human- machine interface
  • Machine learning

ASJC Scopus subject areas

  • Biomedical Engineering


Dive into the research topics of 'Learning algorithms for human-machine interfaces'. Together they form a unique fingerprint.

Cite this