{"id":"W2906568950","doi":"10.15353/jcvis.v4i1.326","title":"ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adaptive resonance theory; Cluster analysis; Computer science; Artificial intelligence; Benchmark (surveying); Image (mathematics); Unsupervised learning; Pattern recognition (psychology); Convolutional neural network; Spectral clustering; Distortion (music); Stability (learning theory); Machine learning; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0007030647,0.0001009339,0.0001786201,0.00009761987,0.0002446871,0.0003237936,0.0002812209,0.00001838301,0.000001671392],"category_scores_gemma":[0.00003303943,0.00007850253,0.00006378224,0.000137629,0.00008432261,0.0006607816,0.0000858414,0.00008853245,0.000003097041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000238896,"about_ca_system_score_gemma":0.00005854559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003120274,"about_ca_topic_score_gemma":2.66507e-7,"domain_scores_codex":[0.9989921,0.00007667064,0.0004101636,0.0001538989,0.0002226225,0.0001445525],"domain_scores_gemma":[0.9984054,0.0004179697,0.0003287588,0.0001118294,0.0006512231,0.00008481884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003566285,0.0001731658,0.000312623,0.0001757095,0.00008288091,0.000026796,0.002405496,0.02416534,0.01280527,0.3469298,0.01867191,0.5938944],"study_design_scores_gemma":[0.0005855203,0.0001733176,0.001223073,0.000150566,0.000006423581,0.0002093674,0.0001162233,0.981223,0.00006745907,0.01190111,0.004247844,0.00009613936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00577889,0.0009207739,0.9914066,0.001050601,0.0004993106,0.0001748489,0.000003730048,0.00002309106,0.0001422192],"genre_scores_gemma":[0.9043893,0.000008178763,0.09473541,0.0003402198,0.0004540968,0.000005444204,8.192367e-7,0.00000850233,0.00005805665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9570576,"threshold_uncertainty_score":0.320124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01238410125520023,"score_gpt":0.2747517400077667,"score_spread":0.2623676387525665,"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."}}