{"id":"W4309166643","doi":"10.1109/tpami.2022.3222104","title":"Geometry Regularized Autoencoders","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Compute Canada; National Institute of General Medical Sciences; Canadian Institute for Advanced Research; National Institutes of Health; National Science Foundation","keywords":"Autoencoder; Artificial intelligence; Nonlinear dimensionality reduction; Feature learning; External Data Representation; Computer science; Representation (politics); Regularization (linguistics); Embedding; Kernel (algebra); Pattern recognition (psychology); Manifold alignment; Manifold (fluid mechanics); Kernel method; Deep learning; Invertible matrix; Machine learning; Mathematics; Dimensionality reduction; Support vector machine","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003033588,0.000195561,0.0002638387,0.0005232077,0.000325867,0.00004120024,0.0002699136,0.0000565636,0.0009313951],"category_scores_gemma":[0.000005267572,0.0001978615,0.0003978717,0.0009029497,0.00007769702,0.000006046623,0.00001541756,0.0002572175,0.000006279376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002817002,"about_ca_system_score_gemma":0.00001946339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006778953,"about_ca_topic_score_gemma":0.0006267615,"domain_scores_codex":[0.9985542,0.0001333168,0.0003000982,0.0005503994,0.0002561353,0.0002058084],"domain_scores_gemma":[0.999194,0.00002199772,0.00009712661,0.0005519231,0.00004686321,0.00008812607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001653222,0.0006986175,0.00203158,0.00002147124,0.003833541,0.00003036668,0.000222386,0.1011348,0.140892,0.00001092059,0.0006072032,0.7503518],"study_design_scores_gemma":[0.0001500705,0.0003816895,0.0003356841,0.000003041344,0.001229456,0.00002510009,0.0001876693,0.03466775,0.9586033,0.00004632595,0.003967426,0.000402462],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03017313,0.0001847483,0.9691263,0.0001327478,0.00003621917,0.0001035136,0.00004330055,0.00004013399,0.000159933],"genre_scores_gemma":[0.9957271,0.0004295498,0.0007654318,0.0007495946,0.00001778159,0.00007264108,0.00007999765,0.00002043593,0.002137527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9683608,"threshold_uncertainty_score":0.9999819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009991200244593062,"score_gpt":0.2626437980890731,"score_spread":0.2526525978444801,"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."}}