{"id":"W3087194612","doi":"10.48550/arxiv.2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Pruning; Computer science; Artificial neural network; Fraction (chemistry); Shuffling; Heuristics; Machine learning; Weighting; Artificial intelligence; Baseline (sea); Layer (electronics); GRASP","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":[0.008710791,0.001989012,0.002257088,0.001024038,0.001861011,0.003972498,0.004231316,0.004897254,0.004385548],"category_scores_gemma":[0.06412955,0.0009681581,0.0008771702,0.001210463,0.00365109,0.01405589,0.002428529,0.009117845,0.003783271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001373028,"about_ca_system_score_gemma":0.001736741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004095098,"about_ca_topic_score_gemma":0.008718717,"domain_scores_codex":[0.9961742,0.001214667,0.0002806269,0.0008815783,0.001132955,0.0003161637],"domain_scores_gemma":[0.9802061,0.009925878,0.001453251,0.004368151,0.003143238,0.0009033504],"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":[0.001296011,0.000278277,0.009594346,0.001080735,0.0004382481,0.0004841153,0.0008461636,0.06317786,0.008991878,0.08266534,0.06653954,0.7646075],"study_design_scores_gemma":[0.0002731792,0.0005034213,0.00390783,0.001517892,0.0003598639,0.00124587,0.0007367005,0.3430867,0.02735306,0.5577221,0.06309165,0.0002017325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05388293,0.02311846,0.8452741,0.05483794,0.002208955,0.0001661077,0.0006291528,0.006918316,0.01296403],"genre_scores_gemma":[0.4851211,0.008857113,0.4762393,0.01389576,0.001778705,0.0002924672,0.001130797,0.003406898,0.009277865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008710791,"threshold_uncertainty_score":0.0460676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1203842908523943,"score_gpt":0.2164573225010282,"score_spread":0.09607303164863397,"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."}}