Deep Feature Learning for EEG Recordings

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.

• Publication year

  2015

• Venue

  arXiv.org

• Publication date

  2015-11-13

• Fields of study

  Medicine, Computer Science

• Identifiers
  arXiv 1511.04306
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Towards Music Imagery Information Retrieval: Introducing the OpenMIIR Dataset of EEG Recordings from Music Perception and Imagination

  2015cited by this paper
• Classifying EEG Recordings of Rhythm Perception

  2014cited by this paper
• EEG-based emotion classification using deep belief networks

  2014cited by this paper
• Learning discriminative features and metrics for measuring action similarity

  2014cited by this paper
• Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction

  2014cited by this paper
• EEG-Based Emotion Recognition Using Deep Learning Network with Principal Component Based Covariate Shift Adaptation

  2014cited by this paper
• Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings

  2014cited by this paper
• Deep Learning using Linear Support Vector Machines

  2013cited by this paper
• Pylearn2: a machine learning research library

  2013cited by this paper
• Deep learning for neuroimaging: a validation study

  2013cited by this paper
• MEG and EEG data analysis with MNE-Python

  2013cited by this paper
• Practical Bayesian Optimization of Machine Learning Algorithms

  2012cited by this paper
• Improving neural networks by preventing co-adaptation of feature detectors

  2012cited by this paper
• Sleep Stage Classification Using Unsupervised Feature Learning

  2012cited by this paper
• Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces

  2011cited by this paper
• Modeling electroencephalography waveforms with semi-supervised deep belief nets: fast classification and anomaly measurement

  2011influential reference
• Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction

  2011cited by this paper
• Classification of patterns of EEG synchronization for seizure prediction.

  2009cited by this paper
• LIBLINEAR: A Library for Large Linear Classification

  2008cited by this paper
• Convolutional Neural Network with embedded Fourier Transform for EEG classification

  2008cited by this paper
• Advances in Neural Information Processing Systems (NIPS)

  2007cited by this paper
• Learning a Distance Metric from Relative Comparisons

  2003cited by this paper
• Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources

  1999influential reference
• Auto-association by multilayer perceptrons and singular value decomposition

  1988influential reference
• Under review as a conference paper at ICLR 2019 softmax Transpose Updated Memory Memory embedded input linear concat Attention Weights concat

  year unknowncited by this paper

• Predicting artificial neural network representations to learn recognition model for music identification from brain recordings

  2025cites this paper
• NeuroClean: A Benchmarking and Optimization Framework for EEG Preprocessing in Semantic Brain-to-Text Decoding

  2025cites this paper
• Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models

  2025cites this paper
• TFDB-EENet: A Time-Frequency Dual-Branch EEG Embedding Network for Multi-Task User Intention Classification

  2025cites this paper
• NeuroSleepNet: A Multi-Head Self-Attention Based Automatic Sleep Scoring Scheme with Spatial and Multi-Scale Temporal Representation Learning

  2024cites this paper
• Deep Learning Models for Diagnosis of Schizophrenia Using EEG Signals: Emerging Trends, Challenges, and Prospects

  2024cites this paper
• A Novel Approach for Analysis and Detection of Depression Using Electroencephalogram (EEG) Signals

  2024cites this paper
• ART: Artifact Removal Transformer for Reconstructing Noise-Free Multichannel Electroencephalographic Signals

  2024cites this paper
• Cramer Distance: A Deep Learning Approach for Better Epileptic Seizure Prediction

  2024cites this paper
• Musical Brainwaves: Decoding Electroencephalography Signals Elicited by Musical Stimuli

  2024cites this paper
• Self-supervised Learning for Electroencephalogram: A Systematic Survey

  2024cites this paper
• Deep Embedded Clustering for Unsupervised Motor Imagery Feature Learning

  2023cites this paper
• Neural decoding of music from the EEG

  2023cites this paper
• CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion

  2023cites this paper
• Multi-Class Image Generation from EEG Features with Conditional Generative Adversarial Networks

  2023cites this paper
• A Deep Learning Approach for Gait Event Detection from a Single Shank-Worn IMU: Validation in Healthy and Neurological Cohorts

  2022cites this paper
• Epilepsy prediction based on PTE and TE of EEG signals using DSC-CNN

  2022cites this paper
• Deep representation of EEG data from Spatio-Spectral Feature Images

  2022cites this paper
• A State-of-the-Art Review of EEG-Based Imagined Speech Decoding

  2022cites this paper
• Eeg Based Visual Classification With Multi-Feature Joint Learning

  2021cites this paper
• Decoding pain from brain activity

  2021cites this paper
• Learning Oculomotor Behaviors from Scanpath

  2021cites this paper
• Music mood and human emotion recognition based on physiological signals: a systematic review

  2021cites this paper
• DeePay: deep learning decodes EEG to predict consumer’s willingness to pay for neuromarketing

  2021cites this paper
• Exploiting sparse representation in the P300 speller paradigm

  2021cites this paper
• Deep Learning Classification Methods for Brain-Computer Interface: An Overview

  2021cites this paper
• Efficient steganalysis using convolutional auto encoder network to ensure original image quality

  2021cites this paper
• Mind the Beat: Detecting Audio Onsets from EEG Recordings of Music Listening

  2021cites this paper
• EEG-based Emotion Recognition with Feature Fusion Networks

  2021cites this paper
• Semi-supervised generative and discriminative adversarial learning for motor imagery-based brain–computer interface

  2021cites this paper
• A Brain-Media Deep Framework Towards Seeing Imaginations Inside Brains

  2021cites this paper
• EEG channel selection strategy for deep learning in emotion recognition

  2021cites this paper
• Evaluating Domain Knowledge and Time Series Features for Automated Detection of Schizophrenia from EEG Signals

  2021cites this paper
• Attention-based Graph ResNet with focal loss for epileptic seizure detection

  2021cites this paper
• The Survey of Image Generation from EEG Signals based on Deep Learning

  2021cites this paper
• Brain-media: A Dual Conditioned and Lateralization Supported GAN (DCLS-GAN) towards Visualization of Image-evoked Brain Activities

  2020cites this paper
• ROS-Neuro Integration of Deep Convolutional Autoencoders for EEG Signal Compression in Real-time BCIs

  2020cites this paper
• GDCNN: A Gated CNN with dilated convolution for decoding steering directions from EEG

  2020cites this paper
• DN3: An open-source Python library for large-scale raw neurophysiology data assimilation for more flexible and standardized deep learning

  2020cites this paper
• Major Depressive Disorder Classification Based on Different Convolutional Neural Network Models: Deep Learning Approach

  2020cites this paper
• An Emotion Recognition Method for Game Evaluation Based on Electroencephalogram

  2020cites this paper
• DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning

  2020cites this paper
• Learning Invariant Representations From EEG via Adversarial Inference

  2020cites this paper
• HybridEEGNet: A Convolutional Neural Network for EEG Feature Learning and Depression Discrimination

  2020cites this paper
• Applying deep learning to single-trial EEG data provides evidence for complementary theories on action control

  2020cites this paper
• Measuring the Depth of Anesthesia Using Ordinal Power Spectral Density of Electroencephalogram

  2020cites this paper
• Morphological feature extraction and KNG‐CNN classification of CT images for early lung cancer detection

  2020cites this paper
• Industry 4.0 Lean Shopfloor Management Characterization Using EEG Sensors and Deep Learning

  2020cites this paper
• The Perils and Pitfalls of Block Design for EEG Classification Experiments

  2020cites this paper
• Information-preserving feature filter for short-term EEG signals

  2020cites this paper
• An Evoked Potential-Guided Deep Learning Brain Representation For Visual Classification

  2020cites this paper
• Epileptic Seizure Prediction in Scalp EEG Using an Improved HIVE-COTE Model

  2020cites this paper
• Graph Convolutional Neural Networks for analysis of EEG signals, BCI application

  2020cites this paper
• Evaluation of Hyperparameter Optimization in Machine and Deep Learning Methods for Decoding Imagined Speech EEG

  2020cites this paper
• Schizophrenia diagnosis using electroencephalographic data

  2019cites this paper
• EmotionMeter: A Multimodal Framework for Recognizing Human Emotions

  2019cites this paper
• Detecting abnormal electroencephalograms using deep convolutional networks.

  2019cites this paper
• Deep learning-based electroencephalography analysis: a systematic review

  2019influential citation
• Deep Learning: Current and Emerging Applications in Medicine and Technology

  2019cites this paper
• EEG correlation at a distance: A re-analysis of two studies using a machine learning approach

  2019cites this paper
• Adversarial Deep Learning in EEG Biometrics

  2019cites this paper
• Recognition of Advertisement Emotions With Application to Computational Advertising

  2019cites this paper
• A Comparative Study of Machine Learning Approaches for Handwriter Identification

  2019cites this paper
• Accurate EEG-Based Emotion Recognition on Combined Features Using Deep Convolutional Neural Networks

  2019influential citation
• A Context-Supported Deep Learning Framework for Multimodal Brain Imaging Classification

  2019cites this paper
• Attention-based Transfer Learning for Brain-computer Interface

  2019cites this paper
• Autoencoder-based transfer learning in brain–computer interface for rehabilitation robot

  2019cites this paper
• A Survey on Deep Learning based Brain Computer Interface: Recent Advances and New Frontiers

  2019cites this paper
• Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals

  2019cites this paper
• Autoencoding of long-term scalp electroencephalogram to detect epileptic seizure for diagnosis support system

  2019cites this paper
• EZSL-GAN: EEG-based Zero-Shot Learning approach using a Generative Adversarial Network

  2019cites this paper
• Deep Learning Based on Event-Related EEG Differentiates Children with ADHD from Healthy Controls

  2019cites this paper
• Adversarial Feature Learning in Brain Interfacing: An Experimental Study on Eliminating Drowsiness Effects

  2019cites this paper
• EPILEPSY PREDICTION USING DEEP LEARNING IN HPC

  2019cites this paper
• Evaluation of NeuCube spiking neural network architecture for MEG/EEG data classification

  2019cites this paper
• A Hierarchical Bidirectional GRU Model With Attention for EEG-Based Emotion Classification

  2019cites this paper
• Predicting the Standard and Deviant Patterns in EEG Signals Based on Deep Learning Model

  2019cites this paper
• Deep Spatial-Temporal Neural Network for Classification of EEG-Based Motor Imagery

  2019cites this paper
• Deep learning models for brain machine interfaces

  2019cites this paper
• EEG-Based Visual Classification with Recurrent Neural Network

  2019cites this paper
• Classification of People who Suffer Schizophrenia and Healthy People by EEG Signals using Deep Learning

  2019cites this paper
• Decoding of Visual Information Based on EEG Data

  2019cites this paper
• EEG-based image classification via a region-level stacked bi-directional deep learning framework

  2019cites this paper
• Exploiting Generalized Matched Filter for Efficient and Effective P300 Detection in Speller Paradigm

  2019cites this paper
• Practical electroencephalography (EEG) applications in stroke rehabilitation: Towards brain-computer interface (BCI) setup and motor function assessment

  2019cites this paper
• International Journal of Recent Technology and Engineering (IJRTE)

  2019cites this paper
• Convolutional neural network, personalised, closed-loop Brain-Computer Interfaces for multi-way control mode switching in real-time

  2018cites this paper
• Deep learning for improved myoelectric control

  2018cites this paper
• Deep Learning and its Importance for Early Signature of Neuronal Disorders

  2018cites this paper
• Deep Feature Learning for EEG Recording Using Autoencoders

  2018cites this paper
• Deep Learning personalised, closed-loop Brain-Computer Interfaces for multi-way classification

  2018cites this paper
• Region level Bi-directional Deep Learning Framework for EEG-based Image Classification

  2018cites this paper
• The Winning Solution to the IEEE CIG 2017 Game Data Mining Competition

  2018cites this paper
• Training on the test set? An analysis of Spampinato et al. [31]

  2018cites this paper
• WearableDL: Wearable Internet-of-Things and Deep Learning for Big Data Analytics - Concept, Literature, and Future

  2018cites this paper
• Deep Learning for Epileptic Spike Detection

  2018cites this paper
• Deep Feature Learning and Visualization for EEG Recording Using Autoencoders

  2018cites this paper
• Learning filter widths of spectral decompositions with wavelets

  2018cites this paper
• Electroencephalography Classification in Brain-Computer Interface with Manifold Constraints Transfer

  2018cites this paper
• Adaptive Adversarial Transfer Learning for Electroencephalography Classification

  2018cites this paper