{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005011705,0.0009813033,0.0006771507,0.0007614673,0.0004136525,0.0005207743,0.001357986,0.0007291881,0.001859772],"category_scores_gemma":[0.002071437,0.0004031424,0.000485746,0.0006181063,0.0005706063,0.000925548,0.0009366035,0.001058692,0.0007325746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004924707,"about_ca_system_score_gemma":0.0008819032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003655148,"about_ca_topic_score_gemma":0.00586006,"domain_scores_codex":[0.9995607,0.00005588821,0.00002971506,0.0001144935,0.0001746844,0.00006462035],"domain_scores_gemma":[0.9993598,0.0002385412,0.00007066787,0.0001517711,0.0001448293,0.00003441752],"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":[0.000219507,0.0001558213,0.001656025,0.000133451,0.00005434403,0.000296892,0.0001579716,0.1759403,0.07812878,0.00830007,0.004013862,0.7309429],"study_design_scores_gemma":[0.00001328442,0.00006825037,0.0006820096,0.00001010095,0.00001506474,0.0001562265,0.00001406751,0.9638404,0.02905229,0.003554983,0.002581253,0.00001200218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0477228,0.0004352165,0.9471522,0.0001050263,0.00004660465,0.00007355493,0.00005780406,0.002330202,0.002076592],"genre_scores_gemma":[0.3922869,0.0003319845,0.6010251,0.0001624412,0.00005265486,0.0001605907,0.0004056826,0.0004348986,0.005139714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003655148,"threshold_uncertainty_score":0.007267714,"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."}}