{"id":"W4386765834","doi":"10.32620/reks.2017.3.06","title":"МЕТОД НАВЧАННЯ БЕЗ ВЧИТЕЛЯ ІЄРАРХІЧНОГО ЕКСТРАКТОРА ВІЗУАЛЬНИХ ОЗНАК НА ОСНОВІ МОДИФІКАЦІЇ НЕЙРОННОГО ГАЗУ","year":2019,"lang":"en","type":"article","venue":"RADIOELECTRONIC AND COMPUTER SYSTEMS","topic":"Enterprise Management and Information Systems","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Computer science; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Coding (social sciences); Binary number; Artificial neural network; Binary code; Partition (number theory); Machine learning; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008579934,0.0005747238,0.0008013031,0.0005747293,0.0003053515,0.001639984,0.0006987451,0.0001933458,0.0002411046],"category_scores_gemma":[0.000007382495,0.0005182925,0.0002202906,0.0005215643,0.00006050413,0.002459669,0.0003891118,0.0003431607,0.00328551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001646811,"about_ca_system_score_gemma":0.00005544719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003584587,"about_ca_topic_score_gemma":0.00002114361,"domain_scores_codex":[0.9965903,0.00005787937,0.0009860173,0.0007172003,0.0006520568,0.0009965312],"domain_scores_gemma":[0.9983729,0.00006566723,0.0006110084,0.0007227212,0.0001628078,0.0000649014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001971761,0.0002480792,0.04547295,0.003931645,0.0009147616,0.00003738845,0.0006852357,0.001050175,0.0001974023,0.5675867,0.3457615,0.03391698],"study_design_scores_gemma":[0.001971594,0.0001396049,0.001973259,0.0002872327,0.00008267773,0.00005698625,0.000290686,0.1697114,0.00001058961,0.0002383577,0.8244215,0.000816097],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5187823,0.01015121,0.1069793,0.001906289,0.02343198,0.006306273,0.00001651451,0.002471663,0.3299545],"genre_scores_gemma":[0.9850112,0.00008372546,0.00007110332,0.00164698,0.005023999,0.00008894093,0.00009872912,0.00007800008,0.007897297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5673484,"threshold_uncertainty_score":0.9997269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004295954374604241,"score_gpt":0.1622266809164084,"score_spread":0.1579307265418041,"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."}}