TY - GEN
T1 - Explainable Deep Learning for Analysing Brain Data
AU - Muller, K. R.
N1 - Funding Information:
The talk will discuss challenges when applying the (recently more and more popular) deep learning methods for BCI data and imaging data (e.g. Sturm et al. 2016, Shen et al 2017). Specifically, I will first briefly introduce the Layer-wise Relevance Propagation (LRP) explanation framework for deep neural networks (Baehrens et al. 2010, Bach et al. 2015, Lapuschkin et al. 2016, Samek et al. 2017b, Montavon et al. 2017, 2018). Then its application to motor imagery BCI data is discussed (Sturm et al. 2016) and I will also report on an upcoming study (Thomas et al 2018) employing DL with explainable LSTMs (Arras et al 2017, for LSTM see Hochreiter and Schmidhuber 1997) to large scale fMRI experimental data from (Van Essen et al 2013) This abstract is based on joint work with Armin Thomas, Wojciech Samek, Hauke Heekeren, Benjamin Blankertz, Gabriel Curio, Michael Tangermann, Siamac Fazli, Vadim Nikulin, Gregoire Montavon, Sebastian Bach/Lapuschkin, Irene Sturm, Arno Villringer, Carmen Vidaurre, Till Nierhaus and many other members of the Berlin Brain Computer Interface team, the machine learning groups and many more esteemed collaborators. We greatly acknowledge funding by BMBF, EU, DFG and NRF.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/2
Y1 - 2019/2
N2 - In this short abstract I will discuss recent directions where deep learning is used for analysing brain imaging data, both in the context of BCI and fMRI-summarizing steps taken by the BBCI team and co-workers. It is the nature of this short text that many pointers to research are given all of which show a high overlap to prior own contributions (this is not only unavoidable but intentional) or will touch upon ongoing unpublished respectively pre-published work.
AB - In this short abstract I will discuss recent directions where deep learning is used for analysing brain imaging data, both in the context of BCI and fMRI-summarizing steps taken by the BBCI team and co-workers. It is the nature of this short text that many pointers to research are given all of which show a high overlap to prior own contributions (this is not only unavoidable but intentional) or will touch upon ongoing unpublished respectively pre-published work.
UR - http://www.scopus.com/inward/record.url?scp=85068345633&partnerID=8YFLogxK
U2 - 10.1109/IWW-BCI.2019.8737321
DO - 10.1109/IWW-BCI.2019.8737321
M3 - Conference contribution
AN - SCOPUS:85068345633
T3 - 7th International Winter Conference on Brain-Computer Interface, BCI 2019
BT - 7th International Winter Conference on Brain-Computer Interface, BCI 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Winter Conference on Brain-Computer Interface, BCI 2019
Y2 - 18 February 2019 through 20 February 2019
ER -