{"id":"W3035732661","doi":"10.24963/ijcai.2020/363","title":"Feature Statistics Guided Efficient Filter Pruning","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Convolutional neural network; Feature selection; Leverage (statistics); Pruning; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); FLOPS; Filter (signal processing); Data mining; Machine learning; Computer vision","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":[0.00002736382,0.00008064293,0.0000738886,0.0000137232,0.00008637778,0.00005855142,0.0005180634,0.00002282874,0.00002720743],"category_scores_gemma":[0.00003489513,0.00006866896,0.00001805282,0.0003636552,0.00001716045,0.00007915267,0.0002379126,0.0001085767,0.0001703285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001272615,"about_ca_system_score_gemma":0.0000168375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.733806e-7,"about_ca_topic_score_gemma":4.93554e-7,"domain_scores_codex":[0.9993021,0.00001486485,0.00008952378,0.0002767845,0.0001461538,0.0001705861],"domain_scores_gemma":[0.9994153,0.00007297345,0.00004065176,0.000301507,0.00004999918,0.0001195317],"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":[0.00000183747,0.00001980622,0.00006188613,0.000007935231,0.000005958916,0.00001430067,0.0004015126,0.0617705,0.00280998,0.4869971,0.4289398,0.01896939],"study_design_scores_gemma":[0.0001072332,0.00002244507,0.0002212749,0.000002571295,0.000001943561,0.000005415794,0.000005994563,0.9069624,0.001879972,0.001239898,0.0894322,0.0001186277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000345466,0.00002133605,0.9747386,0.0218002,0.00005709561,0.0001351066,0.000004845972,0.0002857439,0.002611624],"genre_scores_gemma":[0.07868905,0.00000308057,0.913636,0.006655916,0.00008280666,0.00001371712,0.000005619939,0.000007820566,0.0009059827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8451919,"threshold_uncertainty_score":0.2800239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0354430583203236,"score_gpt":0.2801391617468346,"score_spread":0.244696103426511,"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."}}