What does my network learn? Assessing the interpretability of deep learning for neural signals
Pinar Göktepe-Kavis, Florence M Aellen, Sigurd L Alnes, Athina Tzovara · FENS Forum 2024
In recent years electrophysiological studies have profited from the use of multivariate pattern analysis methods. However, these often rely on outdated classification algorithms. Deep neural networks provide high performance at the cost of interpretability of learned features because of black box approaches. In this project, we evaluated how the interpretability of networks for electroencephalography (EEG) data is affected by the network architecture and the method for feature extraction and visualisation. To this aim, we used two convolutional neural network architectures: (1)ResNet, a residu
ePoster · Neuroscience