{"id":"W4221052463","doi":"10.36227/techrxiv.19357979.v1","title":"Deep Multi-Representation Learning for Data Clustering","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Cluster analysis; Autoencoder; Computer science; Artificial intelligence; Clustering high-dimensional data; Pattern recognition (psychology); Representation (politics); Embedding; Benchmark (surveying); Correlation clustering; Cluster (spacecraft); Subspace topology; AKA; Feature learning; Data mining; Deep learning; Geography","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":[0.002081367,0.001248752,0.001652959,0.002018275,0.0007843864,0.001504792,0.002258884,0.001777695,0.001712639],"category_scores_gemma":[0.004248755,0.0006869929,0.001528487,0.002857215,0.001269556,0.003090948,0.00275647,0.002874256,0.001084804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002380427,"about_ca_system_score_gemma":0.001676889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004954916,"about_ca_topic_score_gemma":0.006316833,"domain_scores_codex":[0.9982941,0.000536358,0.0001084841,0.0005181281,0.0003744025,0.0001685895],"domain_scores_gemma":[0.9985525,0.00041809,0.000190618,0.0004648354,0.0002911788,0.00008276695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001592571,0.0001726286,0.001527113,0.0002572465,0.0002292414,0.00008681857,0.0002045057,0.5180365,0.007055737,0.03660404,0.007519902,0.428147],"study_design_scores_gemma":[0.000004355138,0.00001735629,0.0001633485,0.000009296677,0.000008386618,0.00001850536,0.0000159052,0.977167,0.001537971,0.02012717,0.0009205758,0.00001020094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004531566,0.0004969541,0.9934081,0.0001671288,0.00002364687,0.00002413093,0.00009014459,0.0008323907,0.0004260717],"genre_scores_gemma":[0.3567975,0.0009199713,0.636243,0.000385295,0.0001047935,0.0002353261,0.001466111,0.0002510999,0.00359694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004954916,"threshold_uncertainty_score":0.01727134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1619162002673303,"score_gpt":0.3748241467168809,"score_spread":0.2129079464495506,"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."}}