{"id":"W2943923678","doi":"10.1109/cvprw.2019.00093","title":"Dynamic Representations Toward Efficient Inference on Deep Neural Networks by Decision Gates","year":2019,"lang":"en","type":"article","venue":"","topic":"Hermeneutics and Narrative Identity","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Nvidia","keywords":"FLOPS; Computer science; Artificial neural network; Inference; Deep neural networks; Deep learning; Computation; Artificial intelligence; Reduction (mathematics); Embedding; Speedup; Residual neural network; Computer engineering; Algorithm; Parallel computing; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006741866,0.001145839,0.0009700047,0.0006356682,0.0003498086,0.001380047,0.001880467,0.0009327995,0.003315031],"category_scores_gemma":[0.002380771,0.000661236,0.0008101962,0.0006748304,0.001053137,0.002571037,0.001453108,0.002559657,0.0006739374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001228741,"about_ca_system_score_gemma":0.001513109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004514496,"about_ca_topic_score_gemma":0.007884495,"domain_scores_codex":[0.9995924,0.00008342304,0.00002792148,0.000115111,0.0001045694,0.00007661157],"domain_scores_gemma":[0.9994116,0.0003280202,0.00005614708,0.00008551573,0.00008267257,0.00003607508],"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":[0.0001940601,0.00009371709,0.0006579471,0.0001372272,0.00005582058,0.0001212877,0.00006356146,0.786855,0.007903781,0.06115866,0.003256045,0.1395028],"study_design_scores_gemma":[0.00000673646,0.00001094763,0.00002127972,0.000005155933,0.000004342555,0.000005785147,0.000003285804,0.9841653,0.00132593,0.01413281,0.00031531,0.0000030266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02478765,0.0004972887,0.9695347,0.0003509538,0.00006954199,0.00005712856,0.0002140472,0.002014296,0.00247433],"genre_scores_gemma":[0.6958107,0.0005562377,0.2983297,0.0003471053,0.00008890239,0.0002165759,0.0006692129,0.0001987287,0.003782833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004514496,"threshold_uncertainty_score":0.01108986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02067797506152053,"score_gpt":0.277712747028646,"score_spread":0.2570347719671254,"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."}}