{"id":"W4288318880","doi":"10.48550/arxiv.1906.08746","title":"Progressive Gradient Pruning for Classification, Detection and\\n DomainAdaptation","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Pruning; Computer science; Filter (signal processing); Artificial intelligence; Convolutional neural network; Computational complexity theory; Pattern recognition (psychology); Machine learning; Algorithm; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003344789,0.0005324451,0.0004434325,0.0003317722,0.0009470256,0.0002299701,0.001142482,0.0003842427,0.000005922808],"category_scores_gemma":[0.00007755015,0.0006718843,0.0002154576,0.001148664,0.0003086323,0.0009425124,0.0008975921,0.0005822022,0.00004169719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005749352,"about_ca_system_score_gemma":0.0002227818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002138657,"about_ca_topic_score_gemma":0.00003266806,"domain_scores_codex":[0.9961739,0.0001925871,0.0004664009,0.002405075,0.0001413505,0.000620712],"domain_scores_gemma":[0.9959326,0.0004775384,0.001140934,0.001468365,0.0007109892,0.0002695436],"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":[0.0001983239,0.0001665842,0.0006614805,0.0002644415,0.0001278507,0.00002309205,0.0007789869,0.4566376,0.001801772,0.5071622,0.00004158897,0.03213611],"study_design_scores_gemma":[0.0008591944,0.0002241793,0.004378962,0.0001373729,0.0001508569,0.00001993905,0.000291899,0.9239682,0.0004433424,0.0671057,0.001791559,0.0006287757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1363361,0.000172884,0.8588514,0.0002537081,0.0007082464,0.003250168,0.00001841627,0.0001967921,0.0002123467],"genre_scores_gemma":[0.9860882,0.000379259,0.01228931,0.0000565045,0.0001619765,0.00007097783,0.00004042056,0.00004473576,0.000868678],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8497521,"threshold_uncertainty_score":0.9995732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09234867096554043,"score_gpt":0.2158343628092743,"score_spread":0.1234856918437338,"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."}}