{"id":"W4386472845","doi":"10.1109/tbme.2023.3312361","title":"Resource-Efficient Neural Network Architectures for Classifying Nerve Cuff Recordings on Implantable Devices","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"Neuroscience and Neural Engineering","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"University of Toronto","keywords":"Computer science; Artificial neural network; Neurophysiology; Neural Prosthesis; Artificial intelligence; Engineering; Biomedical engineering; Neuroscience","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004017732,0.0007007305,0.0002708412,0.0003750841,0.0001632621,0.0003843012,0.0006983505,0.0003900293,0.001275812],"category_scores_gemma":[0.001234577,0.0001640341,0.0002802834,0.0003317385,0.0001480082,0.0008047842,0.0003344501,0.0003990894,0.0003515549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005801968,"about_ca_system_score_gemma":0.0004734516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004237231,"about_ca_topic_score_gemma":0.006095878,"domain_scores_codex":[0.9998535,0.00001977154,0.00001419655,0.00003847564,0.00004581986,0.0000283005],"domain_scores_gemma":[0.9996086,0.000127506,0.00006131732,0.00004308259,0.0001450022,0.00001453044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006016897,0.0002208377,0.006785902,0.0002720162,0.0001435784,0.0002773601,0.000085949,0.4030951,0.07516757,0.002097582,0.003553643,0.5076988],"study_design_scores_gemma":[0.000009008001,0.000171414,0.002210267,0.00002013453,0.00003822649,0.00005840461,0.00002803145,0.9731993,0.02215052,0.001014375,0.00108806,0.0000123927],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6261503,0.002409541,0.3625021,0.0004280633,0.0001246592,0.0001060255,0.0006532753,0.003353465,0.004272615],"genre_scores_gemma":[0.9220354,0.0005471562,0.07342548,0.0000738627,0.00002587612,0.00007759784,0.0009742758,0.00004430805,0.002796144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004237231,"threshold_uncertainty_score":0.008425117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03487259350755439,"score_gpt":0.2666617269516684,"score_spread":0.231789133444114,"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."}}