{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/eegnet-a-compact-convolutional-network-for","title":"EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces","arxiv_id":"1611.08024","date":"2016-11-23","proceeding":null,"authors":["Vernon J. Lawhern","Amelia J. Solon","Nicholas R. Waytowich","Stephen M. Gordon","Chou P. Hung","Brent J. Lance"],"abstract":"Brain computer interfaces (BCI) enable direct communication with a computer,\nusing neural activity as the control signal. This neural signal is generally\nchosen from a variety of well-studied electroencephalogram (EEG) signals. For a\ngiven BCI paradigm, feature extractors and classifiers are tailored to the\ndistinct characteristics of its expected EEG control signal, limiting its\napplication to that specific signal. Convolutional Neural Networks (CNNs),\nwhich have been used in computer vision and speech recognition, have\nsuccessfully been applied to EEG-based BCIs; however, they have mainly been\napplied to single BCI paradigms and thus it remains unclear how these\narchitectures generalize to other paradigms. Here, we ask if we can design a\nsingle CNN architecture to accurately classify EEG signals from different BCI\nparadigms, while simultaneously being as compact as possible. In this work we\nintroduce EEGNet, a compact convolutional network for EEG-based BCIs. We\nintroduce the use of depthwise and separable convolutions to construct an\nEEG-specific model which encapsulates well-known EEG feature extraction\nconcepts for BCI. We compare EEGNet to current state-of-the-art approaches\nacross four BCI paradigms: P300 visual-evoked potentials, error-related\nnegativity responses (ERN), movement-related cortical potentials (MRCP), and\nsensory motor rhythms (SMR). We show that EEGNet generalizes across paradigms\nbetter than the reference algorithms when only limited training data is\navailable. We demonstrate three different approaches to visualize the contents\nof a trained EEGNet model to enable interpretation of the learned features. Our\nresults suggest that EEGNet is robust enough to learn a wide variety of\ninterpretable features over a range of BCI tasks, suggesting that the observed\nperformances were not due to artifact or noise sources in the data.","url_abs":"http://arxiv.org/abs/1611.08024v4","url_pdf":"http://arxiv.org/pdf/1611.08024v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/vlawhern/arl-eegmodels","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/Aadhvin02/https-github.com-meagmohit-EEG-Datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/Dekakhrone/EEGNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/JiajZhu/EEGnet_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/LIKANblk/AML_EEG_challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/YundongWang/BCI_Challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/adwaykanhere/FYP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/emotionlab/eegain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/Amir-Hofo/EEGNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/Amir-Hofo/EEGNet_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"eegnet-a-compact-convolutional-network-for","repo_url":"https://github.com/amrzhd/EEGNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"motor-imagery","task_name":"Motor Imagery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.08024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08024"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adwaykanhere/FYP","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YundongWang/BCI_Challenge","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LIKANblk/AML_EEG_challenge","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Aadhvin02/https-github.com-meagmohit-EEG-Datasets","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Amir-Hofo/EEGNet_Pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JiajZhu/EEGnet_Pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amrzhd/EEGNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Dekakhrone/EEGNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vlawhern/arl-eegmodels","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Amir-Hofo/EEGNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/emotionlab/eegain","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"listed":{"samples":8,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"4ee68c136ac5e60f","entry":"make_dataset","repo":"JiajZhu/EEGnet_Pytorch","repo_kind":"listed","path":"EEGnet/Code/dataset.py","file_url":"https://github.com/JiajZhu/EEGnet_Pytorch/blob/HEAD/EEGnet/Code/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4ee68c136ac5e60f"}},{"code_sha256_prefix":"18a7cb1a157b5e64","entry":"ROC","repo":"Dekakhrone/EEGNet","repo_kind":"listed","path":"Utils/Metrics.py","file_url":"https://github.com/Dekakhrone/EEGNet/blob/HEAD/Utils/Metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18a7cb1a157b5e64"}},{"code_sha256_prefix":"5c9bcc29de0f7574","entry":"average_precision","repo":"Dekakhrone/EEGNet","repo_kind":"listed","path":"Utils/Metrics.py","file_url":"https://github.com/Dekakhrone/EEGNet/blob/HEAD/Utils/Metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c9bcc29de0f7574"}},{"code_sha256_prefix":"0f98ec3d18c48979","entry":"clipAxis","repo":"Dekakhrone/EEGNet","repo_kind":"listed","path":"Utils/Augmentations.py","file_url":"https://github.com/Dekakhrone/EEGNet/blob/HEAD/Utils/Augmentations.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f98ec3d18c48979"}},{"code_sha256_prefix":"454576ae95afca9e","entry":"factor","repo":"Dekakhrone/EEGNet","repo_kind":"listed","path":"Utils/DataLoader.py","file_url":"https://github.com/Dekakhrone/EEGNet/blob/HEAD/Utils/DataLoader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"454576ae95afca9e"}},{"code_sha256_prefix":"a3daea9b67047cb5","entry":"getIdxToOversample","repo":"Dekakhrone/EEGNet","repo_kind":"listed","path":"Utils/Augmentations.py","file_url":"https://github.com/Dekakhrone/EEGNet/blob/HEAD/Utils/Augmentations.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3daea9b67047cb5"}},{"code_sha256_prefix":"d5474e0ee287ce88","entry":"permutate","repo":"Dekakhrone/EEGNet","repo_kind":"listed","path":"Utils/DataLoader.py","file_url":"https://github.com/Dekakhrone/EEGNet/blob/HEAD/Utils/DataLoader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d5474e0ee287ce88"}},{"code_sha256_prefix":"201d437326ee5cf9","entry":"splitDataset","repo":"Dekakhrone/EEGNet","repo_kind":"listed","path":"Utils/DataLoader.py","file_url":"https://github.com/Dekakhrone/EEGNet/blob/HEAD/Utils/DataLoader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"201d437326ee5cf9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}