Name
Title | ||
|---|---|---|
Overcoming selective ensemble averaging: unsupervised identification of event-related brain potentials. |
Abstract | ||
|---|---|---|
We present a novel approach to the problem of event-related potential (ERP) identification, based on a competitive artificial neural net- work (ANN) structure. Our method uses ensembled electroencephalogram (EEG) data just as used in conventional averaging, however without the need for a priori data subgrouping into distinct categories (e.g., stimulus- or event-related), and thus avoids conventional assumptions on response invariability. The competitive ANN, often described as a winner takes all neural structure, is based on dynamic competition among the net neurons where learning takes place only with the winning neuron. Using a simple single-layered structure, the proposed scheme results in convergence of the actual neural weights to the embedded ERP patterns. The method is applied to real event-related potential data recorded during a common odd-ball type paradigm. For the first time, within-session variable signal patterns are automatically identified, dismissing the strong and limiting requirement of a priori stimulus-related selective grouping of the recorded data. The results present new possibilities in ERP research. Index Terms—Artificial neural network, evoked electrical comprehen- sive learning. |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/10.844236 | IEEE transactions on bio-medical engineering |
Keywords | Field | DocType |
winning neuron,bioelectric potentials,identification,competitive artificial neural network structure,recorded data,electroencephalography,unsupervised identification,dynamic competition,medical signal processing,common odd-ball type paradigm,automatically identified patterns,net neurons,a priori stimulus-related selective grouping,winner takes all neural structure,embedded erp patterns,simple single-layered structure,stimulus-related category,selective ensemble averaging overcoming,event-related brain potentials,neural nets,learning,within-session variable signal patterns | Convergence (routing),Ensemble averaging,Computer science,A priori and a posteriori,Artificial intelligence,Stimulus (physiology),Artificial neural network,Winner-take-all,Electroencephalography,Machine learning,Limiting | Journal |
Volume | Issue | ISSN |
47 | 6 | 0018-9294 |
Citations | PageRank | References |
7 | 1.01 | 1 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel H. Lange | 1 | 7 | 1.01 |
| Hava T. Siegelmann | 2 | 7 | 1.01 |
| Hillel Pratt | 3 | 7 | 1.35 |
| Inbar, G.F. | 4 | 24 | 4.49 |