{"id":"W4385562814","doi":"10.32920/22734350","title":"Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; Toronto Metropolitan University","funders":"","keywords":"Autoencoder; Cluster analysis; Benchmark (surveying); Artificial intelligence; Centroid; Unsupervised learning; Computer science; Deep learning; Function (biology); Process (computing); Machine learning; Pattern recognition (psychology); Geography; Cartography","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":[0.0001191991,0.0003179164,0.0003149132,0.0002494772,0.00022099,0.0003988737,0.0008099119,0.000316157,0.00006373222],"category_scores_gemma":[0.000008372598,0.0002917294,0.0001306215,0.0004030957,0.0001123617,0.0002819356,0.001051933,0.00055347,0.00006736501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000282334,"about_ca_system_score_gemma":0.0001871349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001274361,"about_ca_topic_score_gemma":0.0008422856,"domain_scores_codex":[0.99793,0.00004812538,0.0004172388,0.001027865,0.0002859692,0.0002907656],"domain_scores_gemma":[0.9982924,0.00003243599,0.0003163339,0.001104715,0.0001434337,0.0001106291],"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":[0.00002010738,0.00004661078,0.0005202934,0.00007139995,0.0001775703,0.00001282788,0.0003268796,0.02448293,0.0002737795,0.01180594,0.0002044645,0.9620572],"study_design_scores_gemma":[0.0001517759,0.0000445456,0.001730439,0.0001011563,0.00002477859,0.0001051341,0.0000960147,0.9634315,0.0005144446,0.03308531,0.0003412704,0.0003735901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002861457,0.00003253253,0.9891394,0.001133943,0.001029048,0.0005082669,0.0000229286,0.003610302,0.001662077],"genre_scores_gemma":[0.08408723,0.0001847,0.9145679,0.00007197698,0.0001162245,0.0003347737,0.00006127261,0.00003853095,0.0005373368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9616836,"threshold_uncertainty_score":0.9999535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01486372253861743,"score_gpt":0.2436237612172311,"score_spread":0.2287600386786137,"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."}}