{"id":"W4403558230","doi":"10.1007/s11222-024-10501-w","title":"Functional autoencoder for smoothing and representation learning","year":2024,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Smoothing; Representation (politics); Artificial intelligence; Computer science; Feature learning; Pattern recognition (psychology); Functional data analysis; Machine learning; Mathematics; Deep learning; Computer vision","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":[],"consensus_categories":[],"category_scores_codex":[0.0001825256,0.00005388711,0.00005661835,0.00005301751,0.0003076793,0.0005618924,0.00003315203,0.00001936818,0.00000123575],"category_scores_gemma":[0.00005720094,0.00005180427,0.00000945835,0.00007990009,0.00002935413,0.0001730782,0.00005118956,0.00009099095,9.502879e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007046474,"about_ca_system_score_gemma":0.0000362911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008593577,"about_ca_topic_score_gemma":5.945745e-7,"domain_scores_codex":[0.9994893,0.00001650173,0.000103801,0.0002243881,0.00006732869,0.00009865622],"domain_scores_gemma":[0.9996079,0.000250723,0.00002989179,0.00003695105,0.00004869395,0.0000258045],"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":[0.000001164543,0.000001771238,0.0002931541,0.00009297229,0.000008125236,0.000002509847,0.0007209368,0.0007007185,0.0001059151,0.1042408,0.0003999125,0.893432],"study_design_scores_gemma":[0.00007821034,0.00002131475,0.0009652779,0.00005096045,0.00000598924,0.00006206409,0.0000723491,0.9637834,0.00005802829,0.03424339,0.0005942491,0.00006469931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004139866,0.0005043366,0.9942973,0.0001796822,0.0005417105,0.00004025746,0.000002454638,0.0001240483,0.0001703588],"genre_scores_gemma":[0.4658305,0.0000134426,0.5337624,0.00003082965,0.0001122787,0.000001765568,0.000005979688,0.000005076701,0.000237722],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9630827,"threshold_uncertainty_score":0.5418341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01745208203611701,"score_gpt":0.2771719733766146,"score_spread":0.2597198913404976,"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."}}