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

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

Multisensory integration in peripersonal space indexes consciousness states in sleep and disorders of consciousness.

Cell reports. Medicine·2026

Same author

Cortical alpha changes during visuospatial attention: a deep learning-enriched EEG analysis.

Cerebral cortex (New York, N.Y. : 1991)·2026

Same author

Inferring Arm Movement Direction from EEG Signals Using Explainable Deep Learning.

Sensors (Basel, Switzerland)·2026

Same author

Propulsion and symmetry within the stroke cycle: a comparison between tethered and free swimming.

The Journal of sports medicine and physical fitness·2026

Same author

On the virtues and limitations of Granger-causal brain connectivity estimate: Critical analysis using neural mass models.

Network neuroscience (Cambridge, Mass.)·2026

Same author

Swimming turns reduce energy demands of the aerobic performance in front crawl.

European journal of applied physiology·2025

Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 19, 2025

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

Interpretable and lightweight convolutional neural network for EEG decoding: Application to movement execution and

Davide Borra¹, Silvia Fantozzi¹, Elisa Magosso¹

¹Department of Electrical, Electronic and Information Engineering "Guglielmo Marconi", University of Bologna, Cesena Campus, Cesena, Italy.

Neural Networks : the Official Journal of the International Neural Network Society

|June 6, 2020

Summary

This summary is machine-generated.

This study introduces Sinc-ShallowNet, a lightweight convolutional neural network (CNN) for electroencephalography (EEG) decoding. It achieves superior performance and interpretability by learning spectral-spatial features, outperforming traditional methods.

Keywords:

Convolutional neural network Electroencephalography Feature learning Interpretability Sinc-convolutional layer

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Related Experiment Videos

Last Updated: Dec 19, 2025

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

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Area of Science:

Neuroscience
Machine Learning
Signal Processing

Background:

Convolutional neural networks (CNNs) show promise for electroencephalography (EEG) decoding by automatically learning features.
Existing CNNs often lack interpretability and have numerous trainable parameters.
Handcrafted features are typically required for traditional EEG decoding methods.

Purpose of the Study:

To propose a lightweight and interpretable shallow CNN (Sinc-ShallowNet) for improved EEG decoding.
To enable direct interpretation of learned spectral-spatial features.
To investigate cognitive/motor aspects with unknown EEG correlates.

Main Methods:

Developed Sinc-ShallowNet, a shallow CNN with a temporal sinc-convolutional layer and a spatial depthwise convolutional layer.
Employed a post-hoc gradient-based technique for enhanced feature interpretation.
Evaluated on benchmark motor-execution and motor-imagery EEG datasets.

Main Results:

Sinc-ShallowNet outperformed traditional machine learning algorithms and other CNNs in EEG decoding.
Learned spectral-spatial features corresponded to known EEG motor-related activity.
Optimal performance was achieved with more temporal kernels and a trialwise training strategy.

Conclusions:

Sinc-ShallowNet offers a parsimonious and interpretable alternative for EEG decoding.
The architecture facilitates the investigation of cognitive/motor processes through EEG analysis.
This approach enhances understanding of EEG correlates for poorly understood cognitive/motor aspects.