Name
Title | ||
|---|---|---|
Divide-and-conquer approach for brain machine interfaces: nonlinear mixture of competitive linear models. |
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1016/S0893-6080(03)00108-4 | Neural Networks |
Keywords | Field | DocType |
smaller nonlinear network,numerical performance comparison,divide-and-conquer strategy,nonlinear network,time-delay neural network,new strategy,linear expert,nonlinear combination,competitive learning,nonlinear mixture,brain machine interface,multiple local linear models,local linear model,competitive linear model,divide-and-conquer approach,brain machine interfaces,nonlinear modeling approach,divide and conquer,neuronal activity,time delay neural network,linear model,multilayer perceptron | Competitive learning,Nonlinear system,Normalization (statistics),Computer science,Linear model,Artificial intelligence,Divide and conquer algorithms,Artificial neural network,Perceptron,Machine learning,Recursion | Journal |
Volume | Issue | ISSN |
16 | 5-6 | 0893-6080 |
Citations | PageRank | References |
17 | 2.42 | 3 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sung-Phil Kim | 1 | 118 | 25.14 |
| Justin C. Sanchez | 2 | 176 | 28.68 |
| Deniz Erdogmus | 3 | 1299 | 169.92 |
| Yadunandana N. Rao | 4 | 122 | 19.57 |
| Johan Wessberg | 5 | 95 | 16.51 |
| Jose C. Principe | 6 | 2295 | 282.29 |
| Miguel A. L. Nicolelis | 7 | 150 | 34.62 |