{"id":"W3085407149","doi":"10.1109/tnnls.2022.3199703","title":"A Progressive Subnetwork Searching Framework for Dynamic Inference","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Subnet; Subnetwork; Computer engineering; Artificial neural network; Inference; Deep learning; Latency (audio); Artificial intelligence; Real-time computing; Parallel computing; Computer network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000435996,0.0002643381,0.0002925455,0.0001353338,0.002719773,0.0002978819,0.0006098643,0.0000843539,0.000008525515],"category_scores_gemma":[0.00001706752,0.0002657917,0.0001167829,0.0008156449,0.00007191998,0.0002787043,0.00002425895,0.001768153,0.000002051785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009219429,"about_ca_system_score_gemma":0.00002804835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001328312,"about_ca_topic_score_gemma":0.00000276221,"domain_scores_codex":[0.9975092,0.0004965644,0.0003558536,0.0007115024,0.0003306944,0.0005961775],"domain_scores_gemma":[0.9972114,0.001872204,0.0002344762,0.0004495182,0.00006611344,0.0001662943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000360096,0.00004332749,0.00003002707,0.00001791714,0.00002192001,0.000008414166,0.0002208803,0.9400617,0.00001601887,0.005218722,0.00002826387,0.05429683],"study_design_scores_gemma":[0.0002472986,0.0004529872,0.00004533024,0.00005698301,0.00001413655,0.000100185,0.0001411759,0.9961962,0.000004438838,0.0008293624,0.001630143,0.0002817761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01066855,0.0009819957,0.9850532,0.0004684717,0.001287003,0.001077957,0.00000811991,0.0004412927,0.00001342035],"genre_scores_gemma":[0.9878917,0.00005577697,0.009643431,0.000163175,0.0001552136,0.001750438,0.000006392218,0.00004169504,0.0002922259],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9772231,"threshold_uncertainty_score":0.9999794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01764554056534982,"score_gpt":0.2917708977516179,"score_spread":0.274125357186268,"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."}}