{"id":"W2996891787","doi":"10.1609/aaai.v34i04.6038","title":"Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Beijing Advanced Innovation Center for Big Data and Brain Computing; National Natural Science Foundation of China","keywords":"Learning vector quantization; Competitive learning; Artificial intelligence; Artificial neural network; Computer science; Vector quantization; Information bottleneck method; Machine learning; Quantization (signal processing); Feature learning; Instance-based learning; Classifier (UML); Pattern recognition (psychology); Unsupervised learning; Algorithm; Cluster analysis","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005109262,0.0002694626,0.0003075958,0.0001064697,0.0004563811,0.0005001758,0.001644596,0.0001066977,0.00003404015],"category_scores_gemma":[0.001390683,0.0002268695,0.0001274442,0.001960447,0.0001431929,0.0004388778,0.0004097696,0.0007978081,0.000136865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004075929,"about_ca_system_score_gemma":0.00008232509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001108596,"about_ca_topic_score_gemma":9.058384e-7,"domain_scores_codex":[0.9975694,0.0000843303,0.000554957,0.0006870252,0.0006157584,0.0004885602],"domain_scores_gemma":[0.9984531,0.0001000864,0.0004857487,0.0001698988,0.0005298941,0.0002612859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001401131,0.00007225812,0.0007206688,0.00004132644,0.00002158864,6.712064e-7,0.007539107,0.1657834,0.02152797,0.7502211,0.0003029267,0.05362881],"study_design_scores_gemma":[0.00004636873,0.000355552,0.0004023911,0.00009383408,0.00001010903,0.000002776367,0.001522238,0.9750769,0.01684616,0.003909486,0.001444944,0.000289206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09301202,0.00004449227,0.8447145,0.01657512,0.0006738597,0.001037535,9.867364e-7,0.0007990287,0.04314241],"genre_scores_gemma":[0.9899594,0.00001386447,0.008531108,0.0009920988,0.000145335,0.00002221235,0.000001688472,0.00002314221,0.0003111268],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8969474,"threshold_uncertainty_score":0.9251469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1110966483058207,"score_gpt":0.280084446335612,"score_spread":0.1689877980297912,"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."}}