{"id":"W2964576881","doi":"10.1609/aaai.v33i01.330110019","title":"Hierarchical Deep Feature Learning for Decoding Imagined Speech from EEG","year":2019,"lang":"en","type":"article","venue":"","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Electroencephalography; Convolutional neural network; Deep learning; Feature (linguistics); Recurrent neural network; Pattern recognition (psychology); Speech recognition; Decoding methods; Channel (broadcasting); Artificial neural network; Algorithm; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001020927,0.0001383491,0.0001681626,0.0000584347,0.0001065378,0.0001603294,0.000333853,0.00007012431,0.0004067347],"category_scores_gemma":[0.0002469151,0.0001083725,0.00008871557,0.0001048257,0.0000355146,0.0001793362,0.0001191288,0.0003258275,0.0002711501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001765674,"about_ca_system_score_gemma":0.00001612954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001476918,"about_ca_topic_score_gemma":0.000008142938,"domain_scores_codex":[0.9988503,0.0000605659,0.0001276425,0.0004832789,0.0001693986,0.0003088429],"domain_scores_gemma":[0.9987676,0.0009006471,0.00004461262,0.0001879009,0.00002330523,0.00007593258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007013508,0.00003603797,0.004475742,0.00001701005,0.000007828231,0.00001160883,0.0003799445,0.0002399247,0.9535795,0.002065452,0.00337494,0.03574183],"study_design_scores_gemma":[0.0009239197,0.0001790376,0.001669836,0.00004039125,0.000008169266,0.00002363391,0.0000917385,0.2081878,0.7435507,0.002831882,0.04217893,0.0003139313],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9540026,0.0000320131,0.03043858,0.002261854,0.0006862076,0.0002882055,0.000005500573,0.0002259485,0.01205907],"genre_scores_gemma":[0.9616876,0.000003720504,0.02472189,0.001687037,0.0001553121,0.000006242854,0.000006303128,0.00002090554,0.01171102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2100288,"threshold_uncertainty_score":0.4453459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01818404080653754,"score_gpt":0.2748584138029164,"score_spread":0.2566743729963789,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}