{"id":"W4303457099","doi":"10.1101/2022.10.05.510983","title":"Resource-efficient Neural Network Architectures for Classifying Nerve Cuff Recordings on Implantable Devices","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neuroscience and Neural Engineering","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Artificial neural network; Convolutional neural network; Cuff; Functional electrical stimulation; Artificial intelligence; Neuroscience; Medicine; Stimulation; Surgery; Biology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007781654,0.0008749641,0.0007604003,0.0004667799,0.001151775,0.0005249978,0.001627447,0.0002834877,0.00003395355],"category_scores_gemma":[0.0007291863,0.0008836402,0.0003721195,0.001114531,0.0001586814,0.00008360443,0.001178909,0.001831891,0.00001590086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002980067,"about_ca_system_score_gemma":0.0002121373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001822097,"about_ca_topic_score_gemma":8.35236e-7,"domain_scores_codex":[0.9943138,0.0002816646,0.000708864,0.002282569,0.0008375609,0.001575482],"domain_scores_gemma":[0.9968348,0.0008645571,0.0005682739,0.001291952,0.00005626,0.0003842174],"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":[0.000185556,0.0001205459,0.000388803,0.0003239219,0.00001682343,0.000137388,0.0000134177,0.2766048,0.7202248,0.0009578402,0.001010947,0.00001515706],"study_design_scores_gemma":[0.0006449909,0.0004277529,0.002978084,0.0004216899,0.00008756916,6.249822e-7,0.000006228238,0.1247767,0.8235208,0.00001372919,0.04544588,0.001676031],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924388,0.0002198056,0.0003316915,0.0002399648,0.004022705,0.001477676,0.0003065211,0.0008924858,0.00007035516],"genre_scores_gemma":[0.9952962,0.00003022135,0.0007115255,0.002049095,0.000983435,0.0006697659,3.787695e-7,0.0002375057,0.00002186595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1518282,"threshold_uncertainty_score":0.9993615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03251148517855394,"score_gpt":0.249094738068911,"score_spread":0.2165832528903571,"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."}}