The DOI matches its Crossref record; 112 of the 112 references it cites were found in a registry or an index; 18 of the 30 sources its claims cite were checked for support.
EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces
Open accessAbstract
OBJECTIVE: Brain-computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional neural networks (CNNs), which have been used in computer vision and speech recognition to perform automatic feature extraction and classification, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. APPROACH: In this work we introduce EEGNet, a compact convolutional neural network for EEG-based BCIs. We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI. We compare EEGNet, both for within-subject and cross-subject classification, to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). MAIN RESULTS: We show that EEGNet generalizes across paradigms better than, and achieves comparably high performance to, the reference algorithms when only limited training data is available across all tested paradigms. In addition, we demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. SIGNIFICANCE: Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks. Our models can be found at: https://github.com/vlawhern/arl-eegmodels.
Overview
CoChat Summary
TL;DR
EEGNet is a compact CNN using depthwise and separable convolutions that generalizes across P300, ERN, MRCP, and SMR BCI paradigms while using far fewer parameters than reference CNNs. It achieves comparable or better performance than state-of-the-art approaches in many within- and cross-subject comparisons and produces neurophysiologically interpretable features.
Key findings
- EEGNet models were up to two orders of magnitude smaller than DeepConvNet and ShallowConvNet: e.g., P300 EEGNet-4,2 had 1,066 parameters vs. 174,127 for DeepConvNet and 104,002 for ShallowConvNet; SMR EEGNet-4,2 had 796 vs. 152,219 and 40,644, respectively.
- Within-subject, EEGNet-4,2 and EEGNet-8,2 did not differ significantly across paradigms (p > 0.05). Both EEGNet models significantly outperformed all other models on MRCP (p < 0.05); EEGNet-8,2 outperformed DeepConvNet, ShallowConvNet, and xDAWN+RG on ERN (p < 0.05); all CNN models outperformed xDAWN+RG on P300 (p < 0.05).
- Cross-subject, all CNN models outperformed xDAWN+RG on P300 (p < 0.05); EEGNet-8,2 and DeepConvNet outperformed ShallowConvNet on MRCP (p < 0.05); xDAWN+RG outperformed all CNN models on ERN (p < 0.05); no significant CNN differences were found for SMR (p > 0.05).
- Feature analyses showed interpretable structure: P300 ablation gave full-model AUC 0.9054, with removal of filters (1,3,4) reducing AUC to 0.7108; SMR spatial filters learned by EEGNet-8,2 correlated with FBCSP filters (e.g., ρ = 0.93, ρ = 0.83, and ρ = −0.93).
Methods
- EEGNet uses temporal convolution, depthwise convolution for frequency-specific spatial filters, and separable convolution, with batch normalization, ELU, dropout, average pooling, and softmax classification; trained with Adam, 500 epochs, validation stopping.
- Evaluated on four datasets: P300 (15 subjects, ~2000 trials/subject, 1–40 Hz), ERN (26 subjects, 340 trials/subject, 1–40 Hz), MRCP (13 subjects, ~1100 trials/subject, 0.1–40 Hz), and SMR (9 subjects, 288 trials/subject, 4–40 Hz).
- Within-subject used four-fold blockwise cross-validation; cross-subject used repeated random folds (30 for P300/MRCP/ERN, 90 for SMR). Comparisons included DeepConvNet, ShallowConvNet, xDAWN+RG for ERP datasets, and FBCSP for SMR, with repeated-measures or one-way ANOVA.
Limitations
- The paper does not state a formal limitations section. Evident from the text: validation is limited to four BCI paradigms/datasets, and cross-subject ERN results show xDAWN+RG significantly outperforming all CNN models.
- The comparison to xDAWN+RG used a single model rather than the original ensemble and omitted dataset-specific “meta features,” as stated by the authors.
- The authors note that ShallowConvNet’s severe underperformance on within-subject MRCP was unexpected and that determining its underlying source will be explored in future research.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
8 Valid · 1 Not valid · 2 Not checked · 61 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“each paradigm relies on manual specification of signal processing [7], feature extraction [8] and classification methods [9], a process which often requires significant subject-matter expertise and/or a priori knowledge about the expected EEG signal.”
What the sources say
- Partly supportedcites [7] Bashashati A, 2007, J. Neural Eng. sourceExperimental — accuracy not yet measured
For the part this citation carries (manual specification of the signal processing), our copy supports the substance: the survey's Section 5.1 (signal enhancement) states that 'the choice of a suitable pre-processing technique however is dependent on several factors such as the recording technology, number of electrodes, and neuromechanism of the BCI', and Section 3 states that 'feature extraction methods used in BCI systems are closely related to the specific neuromechanism(s) used by a BCI' (e.g. VEP-based BCIs extract features to detect the evoked potential in the ongoing EEG), and Section 5.2.2 notes parametric modeling 'require[s] an a priori choice of the structure and order of the signal generation mechanism model'. However, no passage in our copy states that this selection process requires 'significant subject-matter expertise' — the paper frames itself as a reference/taxonomy of methods used (Introduction; Conclusions) rather than characterizing the expertise demand. The expertise clause of the claim is therefore not supported by this source. (LLM, conf=0.72)
- Not checked — no full text of the sourcecites [8] source
- Partly supportedcites [9] Lotte F, 2007, J. Neural Eng. sourceExperimental — accuracy not yet measured
Section 2.2 says that choosing an appropriate classifier requires knowing the properties of available classifiers, and Section 4 provides guidelines for choosing one for a given BCI context. This supports the classification-method selection part attributed to [9], but the paper does not establish that every paradigm requires manual specification or that the process requires significant subject-matter expertise or prior knowledge of the expected EEG signal. Page numbers are unavailable in our copy. (LLM, conf=0.81)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“For all ERP-based data analyses (P300, ERN, MRCP) the traditional approach is the approach which won the Kaggle BCI Competition (code and documentation at http://github.com/alexandrebarachant/bci-challenge-ner-2015), which uses a combination of xDAWN Spatial Filtering [83], Riemannian Geometry [84,85], channel subset selection and L 1 feature regularization”
What the sources say
- Could not verifycites [83] Springenberg J T, 2014 sourceExperimental — accuracy not yet measured
The Experiments section (p. 4) describes image-classification experiments on CIFAR-10, CIFAR-100 and ImageNet. Searches for the Kaggle BCI Competition, ERP/P300 and xDAWN returned no passage in our copy addressing the claimed approach or its components. (LLM, conf=0.78)
- Not checked — no full text of the sourcecites [84] source
- Not checked — no full text of the sourcecites [85] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
Every source the paper cites for this claim was checked and supports it.
In the paper
“Here we see the performances of ShallowConvNet and FBCSP are very similar, replicating previous results as reported in [32], while DeepConvNet performance is significantly lower.”
What the sources say
- Supportedcites [32] source
Result 2 in the Results section says the shallow ConvNet reached accuracies similar to FBCSP, and Table 2 reports closely comparable mean accuracies across subjects. The citation supports the comparison between ShallowConvNet and FBCSP; the citing authors’ observation about their own DeepConvNet result is not attributed to this source. (LLM, conf=0.93)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We see that the EEGNet models are up to two orders of magnitude smaller than both DeepConvNet and ShallowConvNet across all datasets.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“but with two orders of magnitude fewer parameters to fit”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
35 more claims
Create a free account to see all 72 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 20
- Probably not a substantial claim. 15
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It has demonstrated good robustness and has been widely used as a benchmark in EEG analysis”
From A Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection (2024) · cites this paper as [23]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Notably, the EEGNet exhibits exceptional generalization capabilities, displaying the ability to perform well on diverse datasets, and also exhibits robustness to noise, enabling reliable performance even in the presence of noisy input signals [23].”
From A Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection (2024) · cites this paper as [23]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“ensuring the reliability of algorithm”
From IENet: a robust convolutional neural network for EEG based brain-computer interfaces (2022) · cites this paper as [13]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The signal processing of each BCI paradigm requires the participation of relevant prior knowledge [13].”
From IENet: a robust convolutional neural network for EEG based brain-computer interfaces (2022) · cites this paper as [13]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Depthwise and separable convolutions are applied in EEGNet to extract high-dimensional features of EEG, which reduces the number of model parameters to train [13].”
From IENet: a robust convolutional neural network for EEG based brain-computer interfaces (2022) · cites this paper as [13]
Experimental — accuracy not yet measured
17 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 5.1 DeepConvNet and ShallowConvNet architectures · p. 23
“| Conv2D | 200 | (1, 5) | 100 * 200 * C + 200 | Linear | mode = valid, max norm = 2 |”
§ 2.2.1 EEGNet: Compact CNN Architecture · p. 9
“| P300 | 1 | 174,127 | 104,002 | 1,066 | 2,258 |”
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Densely Connected Convolutional Networks
Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2016) · arXiv · doi:10.48550/arxiv.1608.06993 · Cited by 48,960
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“We apply batch normalization [80] along the feature map dimension before applying the exponential linear unit (ELU) nonlinearity [81].”
MethodDelorme, A., & Makeig, S. (2004) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2003.10.009 · Cited by 24,371 · cited 3×
“The data were referenced to linked mastoids, bandpass filtered, using an FIR filter implemented in EEGLAB [53], between 0.”
MethodInfluentialRegularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Research works printed but not linked: 21
- Zander T O, 2011, J. Neural Eng., 8
- Krizhevsky A, 2012, Advances in Neural Information Processing Systems, 1097
- Simonyan K, 2014, CoRR
- Szegedy C, 2014, CoRR
- He K, 2015, CoRR
- Huang G, 2016, CoRR
- Thodoroff P, 2016, CoRR
- Stober S, 2014, Advances in Neural Information Processing Systems 27, 1449
- Stober S, 2015, CoRR
- Bashivan P, 2015, CoRR
- Chollet F, 2016, CoRR
- Abadi M, 2016, Proc. 12th USENIX Conf. on Operating Systems Design and Implementation, 265
- Dyrholm M, 2007, J. Mach. Learn. Res., 8, 1097
- Clevert D, 2015, CoRR
- Srivastava N, 2014, J. Mach. Learn. Res., 15, 1929
- Congedo M, 2013, CoRR
- Baehrens D, 2010, J. Mach. Learn. Res., 11, 1803
- Nguyen A M, 2014, CoRR
- Shrikumar A, 2017, CoRR
- Ancona M, 2018, Int. Conf. on Learning Representations
- 10.1175/1520-0477(1998)079<0061:APGTWA>2.0.CO;2 · DOI · Paper page
Cited by
Deep learning with convolutional neural networks for EEG decoding and visualization
Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F., Burgard, W., & Ball, T. (2017) · Human Brain Mapping · doi:10.1002/hbm.23730 · Cited by 3,751
A review of classification algorithms for EEG-based brain–computer interfaces: A 10 year update
Lotte, F., Bougrain, L., Cichocki, A., Clerc, M., Congedo, M., Rakotomamonjy, A., & Yger, F. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aab2f2 · Cited by 2,239
Deep learning for electroencephalogram (EEG) classification tasks: a review
Craik, A., He, Y., & Contreras-Vidal, J. L. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab0ab5 · Cited by 1,758
“1 FC 20 h 2 OUT [94] CNN ELU (conv) SV P300(1) N/A P300(1) P300(1) 3 conv Softmax (FC) All (64/56/22) 1–40 Hz P300(2) 1–40 Hz MI 4–40 Hz 15 93% 1 FC 0.”
Deep learning-based electroencephalography analysis: a systematic review
Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H., & Faubert, J. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab260c · Cited by 1,532
“The analysis of model activations was used in multiple studies [93, 97, 120, 172, 186, 214, 227, 231].”
MethodEEG Conformer: Convolutional Transformer for EEG Decoding and Visualization
Song, Y., Zheng, Q., Liu, B., & Gao, X. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3230250 · Cited by 1,095
“We use exponential linear units (ELUs) as the activation function for nonlinearity following [17].”
BackgroundMethodInfluential
Metadata
- Authors
- Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., & Lance, B. J.
- Affiliations
- DEVCOM Army Research Laboratory (US)
- Corresponding author
- Lawhern, Vernon J
- Venue
- Journal of Neural Engineering
- Publisher
- IOP Publishing
- Published
- 2018-07-27
- Volume
- 15
- Issue
- 5
- Pages
- 056013
- ISSN
- 1741-2552 (ISSN-L)
- 1741-2560
- OpenAlex
- W2559463885
- Cited by
- 5,115
- References
- 78
- Citations by year
- 2026: 1132 · 2025: 1233 · 2024: 935 · 2023: 649 · 2022: 468 · 2021: 334 · 2020: 212 · 2019: 105 · 2018: 37
- FWCI
- 102.30
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- iopscience.iop.org/info/page/text-and-data-mining (tdm)
- iopscience.iop.org/page/copyright (vor)
- Locations
- Journal of Neural Engineering (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.S. Army Research Laboratory (CAST 076910227001, ARL-74A-HRCYB, ARL-H70-HR52, W911NF-10-2-0022)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
- Keywords
- EEGNet, EEG-based brain-computer interface, compact convolutional neural networks, depthwise separable convolution, error-related negativity, movement-related cortical potentials, sensory motor rhythm, EEG classification, model interpretability, feature visualization, limited training data
- MeSH terms
- Adolescent, Adult, Algorithms, Electroencephalography, Evoked Potentials, Visual, Female, Humans, Male, Middle Aged, Movement, Neural Networks, Computer, Event-Related Potentials, P300, Young Adult, Brain-Computer Interfaces
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. https://app.cochat.ai/papers/10.1088/1741-2552/aace8c
- The paper
- Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., & Lance, B. J. (2018). EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. Journal of Neural Engineering. https://doi.org/10.1088/1741-2552/aace8c
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.