Learning from small datasets-review of workshop 6 of the 10th International BCI Meeting 2023.

Abstract

In a brain-computer interface (BCI), a primary objective is to reduce calibration time by recording as few as possible novel data points to (re-)train decoder models.<i>Objective.</i>Minimizing the calibration can be crucial for enhancing the usability of a BCI application with patients, increasing the acceptance by healthy users, facilitating a fast adaptation during non-stationary recordings, or transferring between sessions.<i>Approach.</i>At the 10th International BCI Meeting in 2023, our workshop addressed the latest proposed techniques to train classification or regression machine learning models with small datasets.<i>Main results.</i>We explored methodologies from both traditional machine learning and deep learning. In addition to talks and discussions, we discussed Python toolboxes for various presented methods and for the benchmarking of classification models.<i>Significance.</i>This review provides a comprehensive overview of the workshop's content and discusses the insights that were obtained.