Abstract
One of the most important building blocks of the brain-machine interface (BMI) based on neuronal spike trains is the decoding algorithm, a computational method for the reconstruction of desired information from spike trains. Previous studies have reported that a simple linear filter is effective for this purpose and that no noteworthy gain is achieved from the use of nonlinear algorithms. In order to test this premise, we designed several decoding algorithms based on the linear filter, and two nonlinear mapping algorithms using multilayer perceptron (MLP) and support vector machine regression (SVR). Their performances were assessed using multiple neuronal spike trains generated by a biophysical neuron model and by a directional tuning model of the primary motor cortex. The performances of the nonlinear algorithms, in general, were superior. The advantages of using nonlinear algorithms were more profound for cases where false-positive/negative errors occurred in spike trains. When the MLPs were trained using trial-and-error, they often showed disappointing performance comparable to that of the linear filter. The nonlinear SVR showed the highest performance, and this may be due to the superiority of SVR in training and generalization.
| Original language | English |
|---|---|
| Pages (from-to) | 202-211 |
| Number of pages | 10 |
| Journal | Journal of Neuroscience Methods |
| Volume | 150 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 2006 Jan 30 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Neuroscience(all)
Cite this
}
Superiority of nonlinear mapping in decoding multiple single-unit neuronal spike trains : A simulation study. / Kim, Kyung Hwan; Kim, Sung Shin; Kim, Sung June.
In: Journal of Neuroscience Methods, Vol. 150, No. 2, 30.01.2006, p. 202-211.Research output: Contribution to journal › Article
TY - JOUR
T1 - Superiority of nonlinear mapping in decoding multiple single-unit neuronal spike trains
T2 - A simulation study
AU - Kim, Kyung Hwan
AU - Kim, Sung Shin
AU - Kim, Sung June
PY - 2006/1/30
Y1 - 2006/1/30
N2 - One of the most important building blocks of the brain-machine interface (BMI) based on neuronal spike trains is the decoding algorithm, a computational method for the reconstruction of desired information from spike trains. Previous studies have reported that a simple linear filter is effective for this purpose and that no noteworthy gain is achieved from the use of nonlinear algorithms. In order to test this premise, we designed several decoding algorithms based on the linear filter, and two nonlinear mapping algorithms using multilayer perceptron (MLP) and support vector machine regression (SVR). Their performances were assessed using multiple neuronal spike trains generated by a biophysical neuron model and by a directional tuning model of the primary motor cortex. The performances of the nonlinear algorithms, in general, were superior. The advantages of using nonlinear algorithms were more profound for cases where false-positive/negative errors occurred in spike trains. When the MLPs were trained using trial-and-error, they often showed disappointing performance comparable to that of the linear filter. The nonlinear SVR showed the highest performance, and this may be due to the superiority of SVR in training and generalization.
AB - One of the most important building blocks of the brain-machine interface (BMI) based on neuronal spike trains is the decoding algorithm, a computational method for the reconstruction of desired information from spike trains. Previous studies have reported that a simple linear filter is effective for this purpose and that no noteworthy gain is achieved from the use of nonlinear algorithms. In order to test this premise, we designed several decoding algorithms based on the linear filter, and two nonlinear mapping algorithms using multilayer perceptron (MLP) and support vector machine regression (SVR). Their performances were assessed using multiple neuronal spike trains generated by a biophysical neuron model and by a directional tuning model of the primary motor cortex. The performances of the nonlinear algorithms, in general, were superior. The advantages of using nonlinear algorithms were more profound for cases where false-positive/negative errors occurred in spike trains. When the MLPs were trained using trial-and-error, they often showed disappointing performance comparable to that of the linear filter. The nonlinear SVR showed the highest performance, and this may be due to the superiority of SVR in training and generalization.
UR - http://www.scopus.com/inward/record.url?scp=31344442525&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=31344442525&partnerID=8YFLogxK
U2 - 10.1016/j.jneumeth.2005.06.015
DO - 10.1016/j.jneumeth.2005.06.015
M3 - Article
C2 - 16099513
AN - SCOPUS:31344442525
VL - 150
SP - 202
EP - 211
JO - Journal of Neuroscience Methods
JF - Journal of Neuroscience Methods
SN - 0165-0270
IS - 2
ER -