Limits...
Mixed-norm regularization for brain decoding.

Flamary R, Jrad N, Phlypo R, Congedo M, Rakotomamonjy A - Comput Math Methods Med (2014)

Bottom Line: For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities.The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection.The multitask approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.

View Article: PubMed Central - PubMed

Affiliation: Laboratoire Lagrange, UMR7293, Université de Nice, 00006 Nice, France.

ABSTRACT
This work investigates the use of mixed-norm regularization for sensor selection in event-related potential (ERP) based brain-computer interfaces (BCI). The classification problem is cast as a discriminative optimization framework where sensor selection is induced through the use of mixed-norms. This framework is extended to the multitask learning situation where several similar classification tasks related to different subjects are learned simultaneously. In this case, multitask learning helps in leveraging data scarcity issue yielding to more robust classifiers. For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities. The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection. The multitask approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.

Show MeSH
Selected sensors for the ERP dataset. The line width of the circle is proportional to the number of times the sensor is selected. No circle means that the sensor has never been selected.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4016929&req=5

fig6: Selected sensors for the ERP dataset. The line width of the circle is proportional to the number of times the sensor is selected. No circle means that the sensor has never been selected.

Mentions: The ErrP dataset differs from the others as its number of examples is small (72 examples per subject). The same experimental protocol as above has been used for evaluating the methods but only 57 examples out of 72 have been retained for validation/training. Classification performances are reported on Table 2. For this dataset, the best performance is achieved by GSVM-2 but the Wilcoxon test shows that all methods are actually statistically equivalent. Interestingly, many channels of this dataset seem to be irrelevant for the classification task. Indeed, GSVM-2 selects only 30% of them while GSVM-a uses only 7% of the channels at the cost of 10% AUC loss. We believe that this loss is essentially caused by the aggressive regularization of GSVM-a and the difficulty to select the regularization parameter λ using only a subset of the 57 training examples. Channels selected by GSVM-2 can be visualized on Figure 6. Despite the high variance in terms of selected sensors, probably due to the small number of examples, sensors in the central area seem to be the most selected one, which is consistent with previous results in ErrP [35].


Mixed-norm regularization for brain decoding.

Flamary R, Jrad N, Phlypo R, Congedo M, Rakotomamonjy A - Comput Math Methods Med (2014)

Selected sensors for the ERP dataset. The line width of the circle is proportional to the number of times the sensor is selected. No circle means that the sensor has never been selected.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4016929&req=5

fig6: Selected sensors for the ERP dataset. The line width of the circle is proportional to the number of times the sensor is selected. No circle means that the sensor has never been selected.
Mentions: The ErrP dataset differs from the others as its number of examples is small (72 examples per subject). The same experimental protocol as above has been used for evaluating the methods but only 57 examples out of 72 have been retained for validation/training. Classification performances are reported on Table 2. For this dataset, the best performance is achieved by GSVM-2 but the Wilcoxon test shows that all methods are actually statistically equivalent. Interestingly, many channels of this dataset seem to be irrelevant for the classification task. Indeed, GSVM-2 selects only 30% of them while GSVM-a uses only 7% of the channels at the cost of 10% AUC loss. We believe that this loss is essentially caused by the aggressive regularization of GSVM-a and the difficulty to select the regularization parameter λ using only a subset of the 57 training examples. Channels selected by GSVM-2 can be visualized on Figure 6. Despite the high variance in terms of selected sensors, probably due to the small number of examples, sensors in the central area seem to be the most selected one, which is consistent with previous results in ErrP [35].

Bottom Line: For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities.The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection.The multitask approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.

View Article: PubMed Central - PubMed

Affiliation: Laboratoire Lagrange, UMR7293, Université de Nice, 00006 Nice, France.

ABSTRACT
This work investigates the use of mixed-norm regularization for sensor selection in event-related potential (ERP) based brain-computer interfaces (BCI). The classification problem is cast as a discriminative optimization framework where sensor selection is induced through the use of mixed-norms. This framework is extended to the multitask learning situation where several similar classification tasks related to different subjects are learned simultaneously. In this case, multitask learning helps in leveraging data scarcity issue yielding to more robust classifiers. For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities. The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection. The multitask approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.

Show MeSH