Graduate Research Talk: Implementing Deep Neural Networks (LSTM) to Implicit BCI
It has been proved that deep neural networks can achieve state-of-the-art results on lots of classic machine learning tasks. However, it is not clear we can achieve the same success in science where we want not only accuracy but also scientific understanding. We present a computational model of affect that can distinguish between spontaneous and posed smiles with a high classification accuracy on a large, popular dataset using deep learning techniques (LSTM). We then apply the deep learning model to the implicit Brain-Computer Interface and test with offline data. We will talk about selection, optimization, and interpretation of existing models and future work/challenges when implementing a real-time BCI framework.