{"id":"W4311282550","doi":"10.7554/elife.76472","title":"Emergent color categorization in a neural network trained for object recognition","year":2022,"lang":"en","type":"article","venue":"eLife","topic":"Categorization, perception, and language","field":"Psychology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Deutsche Forschungsgemeinschaft; York University","keywords":"Categorization; Categorical variable; Artificial intelligence; Convolutional neural network; Categorical perception; Color vision; Computer science; Pattern recognition (psychology); Perception; Object (grammar); Representation (politics); Visual perception; Psychology; Machine learning","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":[0.0003231671,0.0001808916,0.0001456662,0.000127338,0.000163771,0.0002817234,0.0003974866,0.000399799,0.0008906187],"category_scores_gemma":[0.001399162,0.0001335083,0.0002664603,0.0001004793,0.0003875683,0.0005846805,0.0003462939,0.0005942355,0.0001246125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006665111,"about_ca_system_score_gemma":0.0003619596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003136146,"about_ca_topic_score_gemma":0.00452841,"domain_scores_codex":[0.9999182,0.00001086788,0.000002350555,0.00003717597,0.00001121211,0.00002010062],"domain_scores_gemma":[0.9997739,0.00008785893,0.00002664415,0.00004005853,0.0000435855,0.00002790669],"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":[0.0006714916,0.000326318,0.02442927,0.0002044154,0.0001352078,0.000669395,0.0004276372,0.3667989,0.4614168,0.02829115,0.00217456,0.1144549],"study_design_scores_gemma":[0.00001221478,0.00007913771,0.004103446,0.000007198404,0.00001268189,0.00005722603,0.00003939361,0.965006,0.02396861,0.006324026,0.0003816537,0.000008424073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8978227,0.00007299468,0.09801172,0.0003199437,0.00005914267,0.00001970483,0.00009309471,0.0003069831,0.00329361],"genre_scores_gemma":[0.9813471,0.00002353584,0.01715502,0.00005137897,0.000003242451,0.00001389657,0.00008233059,0.00001721034,0.001306259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003136146,"threshold_uncertainty_score":0.006235778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03725297973485506,"score_gpt":0.3105616579016474,"score_spread":0.2733086781667923,"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."}}