{"id":"W3174700868","doi":"10.1609/aaai.v35i9.16978","title":"Linearly Replaceable Filters for Deep Network Channel Pruning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; Electronics and Telecommunications Research Institute","keywords":"FLOPS; Computer science; Pruning; Convolutional neural network; Deep learning; Filter (signal processing); Algorithm; Artificial intelligence; Compensation (psychology); Channel (broadcasting); Computer engineering; Pattern recognition (psychology); Parallel computing; Computer vision; 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":[0.0007588334,0.0009822269,0.0007135345,0.0007852943,0.0004783639,0.0006270843,0.001232658,0.0009584251,0.002442582],"category_scores_gemma":[0.002455147,0.0003172803,0.0006322481,0.0006112981,0.0006681224,0.001473048,0.0007742266,0.00142215,0.000868139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006386011,"about_ca_system_score_gemma":0.00117343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003581871,"about_ca_topic_score_gemma":0.006250398,"domain_scores_codex":[0.9992781,0.0001087219,0.00004117817,0.0001377664,0.0003200005,0.000114247],"domain_scores_gemma":[0.9990281,0.0003420467,0.0001000183,0.000254492,0.0002340059,0.00004134358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005805105,0.0002227385,0.001849567,0.0001701528,0.0001280195,0.0003911278,0.0001315422,0.203242,0.108772,0.02584019,0.006975094,0.651697],"study_design_scores_gemma":[0.00002725463,0.0001150857,0.0003247003,0.00001867489,0.0000437644,0.0002010519,0.00002238262,0.9274209,0.05869316,0.006853538,0.006256139,0.0000234045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02773057,0.0005642934,0.9678786,0.0001004585,0.00007534107,0.00003084308,0.00005887136,0.001806933,0.001754105],"genre_scores_gemma":[0.4140406,0.0005920038,0.5782982,0.0002768581,0.0001261739,0.00010545,0.0003797582,0.0003335282,0.005847495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003581871,"threshold_uncertainty_score":0.008171201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08086057145799233,"score_gpt":0.3017327517650332,"score_spread":0.2208721803070409,"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."}}