{"id":"W4225832902","doi":"10.1609/aaai.v36i7.20745","title":"Top-Down Deep Clustering with Multi-Generator GANs","year":2022,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Esri (Canada)","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Cluster analysis; Computer science; Generator (circuit theory); Artificial intelligence; Data mining; Hierarchical clustering; Embedding; Classifier (UML); Hierarchy; Brown clustering; Spectral clustering; Tree (set theory); Pattern recognition (psychology); Machine learning; Fuzzy clustering; Canopy clustering algorithm; Power (physics); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006095456,0.0005535807,0.0005903397,0.0001925369,0.0004962323,0.0007270395,0.004347567,0.0001838361,0.0003474478],"category_scores_gemma":[0.0002145052,0.0004042422,0.0002525023,0.0006513731,0.0002986879,0.0003519754,0.003747568,0.001076317,0.00002743926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001383279,"about_ca_system_score_gemma":0.0002992862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001432363,"about_ca_topic_score_gemma":0.0001116958,"domain_scores_codex":[0.9966379,0.0000658182,0.0007346149,0.00119889,0.0008089375,0.0005537963],"domain_scores_gemma":[0.9973688,0.00008889234,0.0008087564,0.0007904896,0.0007970236,0.0001460096],"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":[0.0004611719,0.001199646,0.0007796515,0.0005489883,0.0004580827,0.00001718551,0.01280952,0.2731298,0.05098838,0.3508987,0.0007359116,0.3079729],"study_design_scores_gemma":[0.00004443748,0.0002266452,0.0001050119,0.0002386192,0.00004204952,0.000005385855,0.0007056274,0.7878848,0.1999361,0.009966,0.0002798651,0.0005654708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01232518,0.0001074698,0.9752938,0.00302804,0.00186942,0.001074649,0.00002543421,0.0001723703,0.006103689],"genre_scores_gemma":[0.9331552,0.00008333243,0.06557322,0.0003164163,0.0002306299,0.0001649088,0.000002526737,0.00003799199,0.0004357877],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.92083,"threshold_uncertainty_score":0.9998409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07021922864840058,"score_gpt":0.2818315706233342,"score_spread":0.2116123419749337,"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."}}