Deep Feature Learning for EEG Recordings

By Sebastian Stober, Avital Sternin, Adrian M. Owen, Jessica A. Grahn. 2015

137 citations recorded by the source corpus.

We introduce and compare several strategies for learning discriminative features from electroencephalography (EEG) recordings using deep learning techniques. EEG data are generally only available in small quantities, they are high-dimensional with a poor signal-to-noise ratio, and there is considerable variability between individual subjects and recording sessions. Our proposed techniques specifically address these challenges for feature learning. Cross-trial encoding forces auto-encoders to focus on features that are stable across trials. Similarity-constraint encoders learn features that allow to distinguish between classes by demanding that two trials from the same class are more similar to each other than to trials from other classes. This tuple-based training approach is especially suitable for small datasets. Hydra-nets allow for separate processing pathways adapting to subsets of a dataset and thus combine the advantages of individual feature learning (better adaptation of early, low-level processing) with group model training (better generalization of higher-level processing in deeper layers). This way, models can, for instance, adapt to each subject individually to compensate for differences in spatial patterns due to anatomical differences or variance in electrode positions. The different techniques are evaluated using the publicly available OpenMIIR dataset of EEG recordings taken while participants listened to and imagined music.

Subfields: Cognitive Neuroscience, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

Deep learning-based electroencephalography analysis: a systematic review (2019, methodology): “The most frequent model inspection techniques involved the analysis of the trained model’s weights [41, 96, 97, 120, 133, 147, 182, 189, 201, 220, 223, 230, 246].”
Deep learning in bioinformatics (2016, methodology): “Emergent architectures Protein structure [91, 92] Segmentation [141] Brain decoding [169, 170]”
Deep Learning Human Mind for Automated Visual Classification (2016, methodology): “A summary of the adopted experimental paradigm is shown in Table 1.”
EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces (2016, methodology): “eatures, many recent works have explored the application of Deep Learning to EEG signals. For example, CNNs have been used for epilepsy prediction and monitoring [21{25], for auditory music retrieval [26,27], for detection of visual-evoked responses [28{31] and for motor imagery classication [32], w”
Focal Onset Seizure Prediction Using Convolutional Networks (2018, methodology): “Support vector machines [27], random forests [5], autoencoders [28] and other machine learning algorithms combined with feature extraction and selection methods have been applied to the seizure prediction problem.”
Learning Temporal Information for Brain-Computer Interface Using Convolutional Neural Networks (2018, methodology): “[27] used a convolutional autoencoder to pretrain a CNN on the same data set in”
A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series (2017, methodology): “However, this can also be exploited as a leverage to improve the predictive capacities of the algorithm.”