{"id":"W4288102866","doi":"10.48550/arxiv.1909.11832","title":"Adversarial Deep Embedded Clustering: on a better trade-off between\\n Feature Randomness and Feature Drift","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Windsor; Université du Québec à Montréal","funders":"","keywords":"Autoencoder; Cluster analysis; Computer science; Artificial intelligence; Discriminative model; Feature (linguistics); Randomness; Benchmark (surveying); Feature vector; Pattern recognition (psychology); Machine learning; Deep learning; Data mining; Mathematics; Geography","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":[0.0001656605,0.0004320712,0.000497477,0.0002744025,0.0002522985,0.0002066888,0.001298537,0.0007720912,0.00001043463],"category_scores_gemma":[0.00001099743,0.0004576107,0.0002682082,0.0004381845,0.0001015798,0.0002639209,0.001256406,0.001219686,0.00002866112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001215425,"about_ca_system_score_gemma":0.0000754808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001569083,"about_ca_topic_score_gemma":0.00001428225,"domain_scores_codex":[0.9979042,0.0001215128,0.0001673085,0.00133293,0.0001267624,0.0003472211],"domain_scores_gemma":[0.9980427,0.0001377709,0.0002632434,0.001309771,0.00006207454,0.0001844417],"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":[0.003182148,0.001465053,0.02745931,0.002078699,0.003184074,0.001443017,0.007279615,0.2805121,0.00114412,0.3921277,0.06552145,0.2146027],"study_design_scores_gemma":[0.006903987,0.0004684225,0.01104774,0.0003757848,0.0004764432,0.00003968741,0.0001628815,0.9014216,0.001384185,0.02471827,0.05046182,0.002539185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06087264,0.00006094463,0.9339336,0.001506411,0.0004640729,0.0008417179,0.00003276725,0.0004871952,0.001800629],"genre_scores_gemma":[0.9916493,0.0001327189,0.005557362,0.0003914771,0.0002832196,0.000006271727,0.00003400145,0.00002942995,0.001916162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9307767,"threshold_uncertainty_score":0.9997876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0289823917868551,"score_gpt":0.1927971396934436,"score_spread":0.1638147479065885,"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."}}