{"id":"W4213060227","doi":"10.1109/tnnls.2022.3149332","title":"Filter Pruning by Switching to Neighboring CNNs With Good Attributes","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Australian Research Council; Canadian Institute for Advanced Research","keywords":"Pruning; Filter (signal processing); Artificial intelligence; Computer science; Pattern recognition (psychology); Mathematics; Computer vision; Biology; Horticulture","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008601221,0.0002164416,0.000272563,0.0001277334,0.001534444,0.0003924849,0.0003405056,0.00004371083,0.000007588786],"category_scores_gemma":[0.000005213114,0.0001912325,0.00005839954,0.0006182792,0.00001336442,0.0002956947,0.00001327377,0.001069727,0.000001886081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005046523,"about_ca_system_score_gemma":0.00001469818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001694309,"about_ca_topic_score_gemma":0.00001115115,"domain_scores_codex":[0.9977933,0.0006653864,0.0002538325,0.0005206086,0.0003272016,0.0004396551],"domain_scores_gemma":[0.9989617,0.000457463,0.0001115936,0.000286,0.00003570092,0.0001475027],"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":[0.00002344713,0.00002541636,0.001161759,0.00001195871,0.00003014298,0.00001575692,0.0004490397,0.9642574,0.0003392426,0.00007142745,0.00007878323,0.03353564],"study_design_scores_gemma":[0.0003543626,0.0006819259,0.0004621686,0.00007054071,0.00001265157,0.0001421422,0.0002511416,0.9897806,0.00009207693,0.000002603682,0.007826433,0.0003233471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06099144,0.0002947686,0.936689,0.0003903851,0.001047256,0.0002287038,0.000003586414,0.0002776495,0.00007723652],"genre_scores_gemma":[0.9974363,0.00001201231,0.001529018,0.0002486731,0.00009932659,0.0001090492,0.000001966005,0.00002924692,0.0005343535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9364449,"threshold_uncertainty_score":0.9997654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01529511702707572,"score_gpt":0.2331512091427529,"score_spread":0.2178560921156771,"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."}}