{"id":"W4396766218","doi":"10.1371/journal.pone.0301513","title":"Dynamic multilayer growth: Parallel vs. sequential approaches","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Initialization; Computer science; Context (archaeology); Benchmark (surveying); Perceptron; Layer (electronics); Population; Artificial intelligence; Constructive; Artificial neural network; Algorithm; Pattern recognition (psychology); Parallel computing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002272806,0.001158426,0.0007555787,0.0009956686,0.0006056605,0.001584045,0.002035578,0.001302228,0.003779829],"category_scores_gemma":[0.006291821,0.0007289234,0.0009836237,0.0008074147,0.001293394,0.003979765,0.002771474,0.001574933,0.001065874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035779,"about_ca_system_score_gemma":0.0009573528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001884551,"about_ca_topic_score_gemma":0.003367496,"domain_scores_codex":[0.9990934,0.00020791,0.00006230987,0.0002084473,0.0003153778,0.0001126139],"domain_scores_gemma":[0.9969195,0.001482193,0.0002878537,0.0006631343,0.0004927922,0.0001545172],"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":[0.0002566095,0.0001406535,0.001768897,0.0003864021,0.0000970231,0.0002150774,0.0004119671,0.4179608,0.02212486,0.0884817,0.003629659,0.4645264],"study_design_scores_gemma":[0.00002599449,0.0001082913,0.0002467785,0.00003731684,0.00004388243,0.0001785086,0.0000880245,0.9392886,0.01034096,0.04382433,0.005796733,0.00002053743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0193731,0.0008052716,0.9720609,0.000402139,0.00008653737,0.00009448826,0.00004633372,0.0007231079,0.006408242],"genre_scores_gemma":[0.3862413,0.001124067,0.603582,0.000231048,0.000136273,0.0003212595,0.0001526109,0.000491775,0.007719702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003779829,"threshold_uncertainty_score":0.01264477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09221602388305478,"score_gpt":0.2469199991863249,"score_spread":0.1547039753032702,"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."}}