뇌공학 BK21 초청 세미나가 아래와 같이 7월 10일에 진행되오니 관심 있는 분들의 많은 참석 부탁드립니다.
- 아 래 -
연사: Marco Congedo 박사 (National Center for Scientific Research)
제목: Riemannian Geometry for Classification of EEG-based Brain-Computer Interface Data
일시: 2017년 7월 10일 (월), 오전 11시
장소: 우정정보통신관 604호
주최: 고려대학교 대학원 뇌공학과, 고려대학교 BK21 뇌공학사업단
후원: 고려대학교 뇌공학연구소
Despite its short history, the use of Riemannian geometry in brain-computer interface (BCI) decoding is currently attracting increasing attention, due to an accumulating documentation of its simplicity, accuracy, robustness and transfer learning capabilities, including the winning score obtained in five recent international predictive modeling BCI data competitions. The Riemannian framework is sharp from a mathematical perspective, yet in practice it is simple, both algorithmically and computationally. This allows the conception of online decoding machines suiting real-world operation in adverse conditions. In this talk we will review elements of Riemannian geometry useful for BCI decoding and we will illustrate the principles for its use as BCI classifier, both in theory and with real-data examples. We will also provide rationale for the robustness of the method and its transfer learning capabilities. Links to available open-source Matlab and Python code libraries for designing BCI decoders will be given.