{"id":"W2883207092","doi":"","title":"Aggregated Learning: A Vector Quantization Approach to Learning with Neural Networks.","year":2018,"lang":"en","type":"preprint","venue":"NPARC","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Vector quantization; Quantization (signal processing); Artificial neural network; Learning vector quantization; Equivalence (formal languages); Computer science; Artificial intelligence; Smoothing; Algorithm; Mathematics; Theoretical computer science; Machine learning; Discrete mathematics; Computer vision","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001954737,0.0008571416,0.001085115,0.0009130404,0.0004465552,0.001401787,0.002385062,0.001023271,0.003091953],"category_scores_gemma":[0.008105349,0.000401749,0.0005810504,0.001199452,0.001408604,0.004135484,0.003088168,0.00281978,0.0006394687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001239655,"about_ca_system_score_gemma":0.0008549018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00211345,"about_ca_topic_score_gemma":0.002429291,"domain_scores_codex":[0.9990703,0.0003479361,0.00005247787,0.000201892,0.0002656624,0.00006167643],"domain_scores_gemma":[0.9982254,0.0008120065,0.0001592956,0.0004194621,0.0002816783,0.0001021216],"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":[0.0001301543,0.0001161731,0.001125946,0.0003304141,0.0001640758,0.00007326232,0.0002541069,0.452816,0.003935874,0.2876754,0.009510953,0.2438677],"study_design_scores_gemma":[0.000006494268,0.00002590167,0.0000894971,0.00001483624,0.000009440656,0.00001410781,0.00001116039,0.8553038,0.001030175,0.1421213,0.001366599,0.000006652347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005196522,0.0007150376,0.9915739,0.0002768421,0.00008492565,0.00003095932,0.0001140533,0.0004325547,0.001575287],"genre_scores_gemma":[0.5405033,0.001384625,0.4498392,0.0006803876,0.0003873391,0.0002950503,0.0007685557,0.0002937716,0.005847837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003091953,"threshold_uncertainty_score":0.01034361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02594470968825211,"score_gpt":0.2457944996584171,"score_spread":0.219849789970165,"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."}}