{"id":"W4403370751","doi":"10.48550/arxiv.2408.02654","title":"On Using Quasirandom Sequences in Machine Learning for Model Weight Initialization","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Initialization; Computer science; Artificial intelligence; Mathematics; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005330091,0.001391852,0.0007380353,0.0008846772,0.0006108758,0.001003412,0.001198459,0.00101872,0.001240861],"category_scores_gemma":[0.02306089,0.0006681914,0.000591081,0.000806459,0.001506142,0.003436588,0.001339987,0.002391385,0.000730986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028021,"about_ca_system_score_gemma":0.001296703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003420431,"about_ca_topic_score_gemma":0.006202062,"domain_scores_codex":[0.9975205,0.001614292,0.0001192297,0.0003460093,0.0003105381,0.00008942857],"domain_scores_gemma":[0.9888475,0.007759842,0.0007182792,0.001743127,0.0008078302,0.0001234548],"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":[0.0002898764,0.0001248362,0.003768755,0.0001580572,0.00009245941,0.00008803694,0.0001200785,0.8680195,0.004297425,0.02079433,0.002068273,0.1001784],"study_design_scores_gemma":[0.00003145119,0.0001203623,0.0004028348,0.00002777366,0.00001269361,0.00003520988,0.0000131117,0.9850206,0.003691675,0.00982932,0.0007981474,0.00001684484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08557446,0.001509855,0.9066662,0.0009293366,0.0001124587,0.0001563495,0.0001574529,0.002072144,0.002821681],"genre_scores_gemma":[0.5666773,0.0009963367,0.428315,0.000493548,0.00007732474,0.0003872229,0.0007371384,0.0006171486,0.001698816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005330091,"threshold_uncertainty_score":0.02818853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1229236932282941,"score_gpt":0.2316172784156684,"score_spread":0.1086935851873743,"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."}}