{"id":"W2789613043","doi":"10.1109/globalsip.2017.8309176","title":"Activation pruning of deep convolutional neural networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pruning; Convolutional neural network; Implementation; Latency (audio); Deep neural networks; Constraint (computer-aided design); Artificial intelligence; Deep learning; Machine learning; Telecommunications","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":[0.00006028931,0.00006082187,0.00007383862,0.00002305057,0.0003407072,0.0000614118,0.0007949416,0.00002925872,0.00001143444],"category_scores_gemma":[0.0000354664,0.00005644413,0.0000284868,0.0000780082,0.00007495035,0.0007672514,0.0002476886,0.00007908387,0.000003864909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001479087,"about_ca_system_score_gemma":0.000008920207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000092911,"about_ca_topic_score_gemma":0.000005869691,"domain_scores_codex":[0.9994248,0.00001255926,0.0001311066,0.0001790891,0.0001163266,0.0001361227],"domain_scores_gemma":[0.9989556,0.00008068589,0.0001988214,0.0006513094,0.00007482423,0.00003874902],"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":[0.000005121156,0.00003193637,0.003664499,0.00000294532,0.000008424755,6.335136e-7,0.00004322271,0.1591097,0.002323018,0.7182547,0.0002905976,0.1162652],"study_design_scores_gemma":[0.0001014108,0.00001146811,0.03181725,0.000003137912,0.000001044507,0.00000237163,0.000002215735,0.9614345,0.001301499,0.005024415,0.0002398813,0.00006072975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008856973,0.00001429168,0.9864121,0.001112698,0.0001058719,0.00009808769,1.738359e-7,0.00007235047,0.00332746],"genre_scores_gemma":[0.9419401,0.000002935373,0.05771953,0.00013305,0.00007211015,0.00001231215,0.000001785468,0.000003506368,0.0001146228],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9330832,"threshold_uncertainty_score":0.2620479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02507840189358176,"score_gpt":0.2811562029342635,"score_spread":0.2560778010406817,"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."}}