{"id":"W4387618741","doi":"10.1016/j.patter.2023.100844","title":"Nonlinear independent component analysis for principled disentanglement in unsupervised deep learning","year":2023,"lang":"en","type":"review","venue":"Patterns","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Precursory Research for Embryonic Science and Technology; Japan Science and Technology Agency; Japan Society for the Promotion of Science; Academy of Finland; Canadian Institute for Advanced Research","keywords":"Independent component analysis; Identifiability; Nonlinear system; Heuristic; Artificial intelligence; Computer science; Unsupervised learning; Representation (politics); Component (thermodynamics); Feature learning; Machine learning; Probabilistic logic; Uniqueness; Deep learning; Pattern recognition (psychology); Algorithm; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001414099,0.001158299,0.001039914,0.002371413,0.0003213027,0.001251653,0.00151004,0.001662837,0.004251499],"category_scores_gemma":[0.002457997,0.0005989308,0.0008540151,0.003907558,0.001968041,0.002396056,0.001097702,0.003342522,0.003428004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001112763,"about_ca_system_score_gemma":0.001329361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001342362,"about_ca_topic_score_gemma":0.001325569,"domain_scores_codex":[0.9993877,0.000125214,0.00004689219,0.0001415899,0.0002754223,0.00002304829],"domain_scores_gemma":[0.9988261,0.0007512521,0.00007575982,0.00007637215,0.0002400585,0.00003056094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003149589,0.00006411682,0.0002869752,0.004210968,0.0001209114,0.0001050409,0.00006898709,0.008504851,0.001669413,0.1191724,0.02088393,0.8448809],"study_design_scores_gemma":[0.00002313781,0.0001001,0.001108014,0.002891832,0.0001298252,0.001038917,0.00006967264,0.04078341,0.005292493,0.1802645,0.7681642,0.0001338993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0007516484,0.7138472,0.267315,0.002462786,0.000909518,0.00007575989,0.0001354718,0.0003199036,0.01418273],"genre_scores_gemma":[0.01764431,0.8479246,0.1260349,0.0009724038,0.001562601,0.0001890447,0.0002782237,0.0001157157,0.005278218],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.004251499,"threshold_uncertainty_score":0.01422274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09468974548462399,"score_gpt":0.374004057197054,"score_spread":0.27931431171243,"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."}}