Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Feb 25, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Deep learning with convolutional neural networks for EEG decoding and visualization.

Robin Tibor Schirrmeister^1,2, Jost Tobias Springenberg^2,3, Lukas Dominique Josef Fiederer^1,2,4

¹Translational Neurotechnology Lab, Epilepsy Center, Medical Center - University of Freiburg, Engelberger Str. 21, Freiburg, 79106, Germany.

Human Brain Mapping

|August 8, 2017

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Transcriptome-based cell type assignment for kidney cell culture models.

bioRxiv : the preprint server for biology·2026

Same author

Interpretable and granular video-based quantification of motor characteristics from the finger-tapping test in Parkinson's disease.

NPJ Parkinson's disease·2026

Same author

Advancing biogeographical ancestry predictions through machine learning.

Forensic science international. Genetics·2025

Same author

Learning from small datasets-review of workshop 6 of the 10th International BCI Meeting 2023.

Journal of neural engineering·2025

Same author

Influence of pitch modulation on event-related potentials elicited by Dutch word stimuli in a brain-computer interface language rehabilitation task.

Journal of neural engineering·2025

Same author

Dareplane: a modular open-source software platform for BCI research with application in closed-loop deep brain stimulation.

Journal of neural engineering·2025

Same journal

Benchmarking fMRI Denoising Pipelines.

Human brain mapping·2026

Same journal

Modeled Long-Term Effects of Psilocybin on Dynamic Activity and Effective Connectivity of Fronto-Striatal-Thalamic Circuits.

Human brain mapping·2026

Same journal

Intrinsic Functional Architecture Reflects Individual Differences in Passive Working Memory: An Exploratory Resting-State fMRI Study.

Human brain mapping·2026

Same journal

Symptom Overlap and Neurobiological Similarities Between Posttraumatic Stress Disorder and Tinnitus.

Human brain mapping·2026

Same journal

Test-Retest Reliability of Sensorimotor Activity Measured With Spinal Cord fMRI.

Human brain mapping·2026

Same journal

The Human Visual Claustrum Responses to Physical Stimulus Properties and Subjective Content During Movie Viewing.

Human brain mapping·2026

See all related articles

This summary is machine-generated.

Deep ConvNets effectively decode tasks from raw electroencephalography (EEG) data without handcrafted features. Novel visualization methods reveal ConvNets learn spectral power modulations for brain mapping.

Area of Science:

Neuroscience
Machine Learning
Biomedical Engineering

Background:

Deep convolutional neural networks (deep ConvNets) excel in computer vision via end-to-end learning.
End-to-end electroencephalography (EEG) analysis using deep ConvNets is gaining interest.
Optimal design, training, and feature visualization for EEG decoding with deep ConvNets require further study.

Purpose of the Study:

To investigate deep ConvNet architectures for end-to-end EEG decoding of imagined or executed tasks.
To develop novel methods for visualizing informative EEG features learned by deep ConvNets.
To compare deep ConvNet performance against established methods like Filter Bank Common Spatial Patterns (FBCSP).

Main Methods:

Studied various deep ConvNet architectures for raw EEG decoding.

Keywords:

EEG analysis brain mapping brain-computer interface brain-machine interface electroencephalography end-to-end learning machine learning model interpretability

More Related Videos

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Related Experiment Videos

Last Updated: Feb 25, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Incorporated machine learning advancements: batch normalization and exponential linear units.

Employed a cropped training strategy to enhance performance.

Developed new visualization techniques to interpret learned EEG features.

Main Results:

Deep ConvNets achieved high decoding accuracies (84.0%), comparable to FBCSP (82.1%).
Visualization confirmed ConvNets learn spectral power modulations in alpha, beta, and high gamma frequencies.
Feature visualization enabled spatial mapping of causal contributions across frequency bands.

Conclusions:

Deep ConvNets can decode task-related information from raw EEG without manual feature engineering.
Advanced visualization techniques offer insights into ConvNet feature learning for EEG.
Deep ConvNets show significant potential for EEG-based brain mapping applications.