{"id":"W2963896595","doi":"10.1109/cvpr.2018.00908","title":"SBNet: Sparse Blocks Network for Fast Inference","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; FLOPS; Computation; Convolution (computer science); Speedup; Convolutional neural network; Inference; Artificial intelligence; Leverage (statistics); Object detection; Pattern recognition (psychology); Algorithm; Parallel computing; Artificial neural network","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":[0.00008786805,0.0001096497,0.0001017385,0.00002351532,0.0002376434,0.00006727533,0.0008058992,0.00004017019,0.00004696143],"category_scores_gemma":[0.00002451345,0.00009643231,0.00003807597,0.0004419975,0.00008247213,0.0002436885,0.0002303603,0.0000623942,0.0001682618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001470781,"about_ca_system_score_gemma":0.0000283862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004955916,"about_ca_topic_score_gemma":0.00006271568,"domain_scores_codex":[0.9989845,0.00001101065,0.0001619364,0.0003717901,0.0001026369,0.0003681033],"domain_scores_gemma":[0.9988578,0.0002058814,0.00006254905,0.0006510867,0.0001282262,0.00009447306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000079425,0.00004132003,0.0005517391,0.000002997094,0.00001003352,7.583512e-7,0.0001198766,0.004156672,0.0005068344,0.774938,0.07749084,0.1421729],"study_design_scores_gemma":[0.0003081312,0.0002205292,0.0009673634,0.00001303928,0.000005367437,0.000007464585,0.000005672634,0.5151667,0.003041945,0.1572287,0.3226975,0.0003376176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009751062,0.00002362555,0.9888032,0.001117457,0.000269475,0.0003241898,0.000001705853,0.0003047497,0.00818049],"genre_scores_gemma":[0.4100507,0.000007889953,0.5849255,0.001558558,0.000809108,0.0001275822,0.000002656251,0.000009322936,0.002508654],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6177094,"threshold_uncertainty_score":0.3932396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03360285784287599,"score_gpt":0.2991795134082915,"score_spread":0.2655766555654155,"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."}}