Search: onr:"swepub:oai:gup.ub.gu.se/111968" >
Divide-and-conquer ...
Divide-and-conquer approach for brain machine interfaces: nonlinear mixture of competitive linear models.
-
Kim, Sung-Phil (author)
-
Sanchez, Justin C (author)
-
Erdogmus, Deniz (author)
-
show more...
-
Rao, Yadunandana N (author)
-
- Wessberg, Johan, 1962 (author)
- Gothenburg University,Göteborgs universitet,Institutionen för fysiologi och farmakologi, Avdelningen för fysiologi,Institute of Physiology and Pharmacology, Dept of Physiology
-
Principe, Jose C (author)
-
Nicolelis, Miguel (author)
-
show less...
-
(creator_code:org_t)
- 2003
- 2003
- English.
-
In: Neural networks : the official journal of the International Neural Network Society. - 0893-6080. ; 16:5-6, s. 865-71
- Related links:
-
https://gup.ub.gu.se...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- This paper proposes a divide-and-conquer strategy for designing brain machine interfaces. A nonlinear combination of competitively trained local linear models (experts) is used to identify the mapping from neuronal activity in cortical areas associated with arm movement to the hand position of a primate. The proposed architecture and the training algorithm are described in detail and numerical performance comparisons with alternative linear and nonlinear modeling approaches, including time-delay neural networks and recursive multilayer perceptrons, are presented. This new strategy allows training the local linear models using normalized LMS and using a relatively smaller nonlinear network to efficiently combine the predictions of the linear experts. This leads to savings in computational requirements, while the performance is still similar to a large fully nonlinear network.
Subject headings
- MEDICIN OCH HÄLSOVETENSKAP -- Medicinska och farmaceutiska grundvetenskaper -- Fysiologi (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Basic Medicine -- Physiology (hsv//eng)
Keyword
- Artificial Intelligence
- Brain
- physiology
- Nonlinear Dynamics
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database