{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007469897,0.0006282009,0.0005221093,0.0004762323,0.0002734215,0.0004642181,0.0009321953,0.000637398,0.0009538834],"category_scores_gemma":[0.003055711,0.0003611756,0.0003105602,0.0004720686,0.0003999006,0.0007365222,0.0005934691,0.000896039,0.000280824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004062942,"about_ca_system_score_gemma":0.0006068954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002061846,"about_ca_topic_score_gemma":0.002757498,"domain_scores_codex":[0.9995821,0.0001044599,0.00003507872,0.00006711874,0.0001500962,0.00006118835],"domain_scores_gemma":[0.9991269,0.0004724683,0.00008473779,0.0001167528,0.0001732602,0.00002600573],"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":[0.0004063809,0.00009320501,0.002163997,0.0002856382,0.00007319416,0.0004328083,0.0001492761,0.47739,0.05192152,0.0162338,0.002982926,0.4478673],"study_design_scores_gemma":[0.00001734568,0.00006931691,0.0009007964,0.00003751873,0.00002868527,0.0001461282,0.00001853463,0.9606885,0.02588236,0.009071064,0.003130282,0.000009402555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1946448,0.004846159,0.7927606,0.0004088824,0.000160311,0.00006839108,0.0001469836,0.001835669,0.005128292],"genre_scores_gemma":[0.8404391,0.001709399,0.1534265,0.0001543588,0.00005361202,0.0000755696,0.0002738069,0.0001594672,0.003708109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002061846,"threshold_uncertainty_score":0.004099667,"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."}}