{"id":"W2128822792","doi":"10.1186/1471-2202-8-s2-p205","title":"Unsupervised learning is crucial to learning the names of objects","year":2007,"lang":"en","type":"article","venue":"BMC Neuroscience","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Unsupervised learning; Discriminative model; Machine learning; Artificial neural network; Supervised learning; Competitive learning; Exploit; Pattern recognition (psychology)","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":[0.0005462936,0.0000977475,0.0001005634,0.00006962119,0.0004834818,0.0001342707,0.001310941,0.00002274079,0.000004181064],"category_scores_gemma":[0.0002211353,0.00007175007,0.00005485354,0.001376616,0.0001142964,0.0002144589,0.0003794879,0.0002211864,0.00002237347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009208467,"about_ca_system_score_gemma":0.00005435424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001562745,"about_ca_topic_score_gemma":0.00001371361,"domain_scores_codex":[0.9986077,0.00006535346,0.0002056758,0.0004145418,0.0003628125,0.0003439082],"domain_scores_gemma":[0.9990974,0.0002647148,0.00009335704,0.0003763525,0.00005925608,0.0001089207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003072978,0.0001648094,0.04535427,0.00003294007,0.000002599282,0.00001903679,0.007840995,0.09132878,0.6799033,0.04908395,0.00161129,0.1246274],"study_design_scores_gemma":[0.0005229622,0.0008037879,0.3077371,0.00007902873,0.00001086326,0.00006756194,0.0005300909,0.429009,0.1569115,0.001396165,0.102147,0.0007849293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4618629,0.00003604444,0.5349059,0.0009508723,0.0003453519,0.0002357794,3.760201e-7,0.0001232829,0.00153954],"genre_scores_gemma":[0.993084,0.000007970637,0.004434805,0.001591709,0.00007133457,0.000007991742,8.568468e-8,0.000006060239,0.0007960513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5312212,"threshold_uncertainty_score":0.37186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02773347381378027,"score_gpt":0.2805868887266423,"score_spread":0.2528534149128621,"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."}}