{"id":"W4388934007","doi":"10.1088/1361-6420/ad0f3b","title":"DRIP: deep regularizers for inverse problems","year":2023,"lang":"en","type":"article","venue":"Inverse Problems","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Israeli Centers for Research Excellence; Division of Chemistry; Council for Higher Education; Ben-Gurion University of the Negev; United States-Israel Binational Science Foundation","keywords":"Deblurring; Inverse problem; Regularization (linguistics); Mathematics; Inference; Scalar (mathematics); Applied mathematics; Inverse; Well-posed problem; A priori and a posteriori; Function (biology); Mathematical optimization; Algorithm; Image (mathematics); Calculus (dental); Computer science; Artificial intelligence; Image restoration; Image processing; Mathematical analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001804959,0.0009058719,0.0008341634,0.000663765,0.0003189809,0.001005245,0.001350005,0.001651462,0.003086864],"category_scores_gemma":[0.005137135,0.0005984962,0.0007212472,0.0005423638,0.0014857,0.001546349,0.002837384,0.003280625,0.001074512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000653439,"about_ca_system_score_gemma":0.0008561258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00144441,"about_ca_topic_score_gemma":0.002051616,"domain_scores_codex":[0.9992862,0.0002687092,0.00003282686,0.000115875,0.000239139,0.00005723889],"domain_scores_gemma":[0.9986939,0.0007352331,0.0001194937,0.0001923408,0.0001872404,0.0000717396],"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":[0.000130704,0.00008579352,0.0005070014,0.0001968215,0.00007288454,0.0001186436,0.00008992112,0.7253259,0.009014699,0.1413839,0.008825139,0.1142486],"study_design_scores_gemma":[0.000007296037,0.00001479714,0.00003423093,0.00001115041,0.000002788001,0.00001916014,0.00000491823,0.9774605,0.001154759,0.01948087,0.001804959,0.000004614481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003753104,0.0001944871,0.9934928,0.0002394314,0.0000353383,0.00002020833,0.00005878328,0.000422672,0.001783242],"genre_scores_gemma":[0.2663707,0.0007009442,0.7191939,0.0006169759,0.0001710324,0.0002908463,0.0005089885,0.0006939626,0.01145266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003086864,"threshold_uncertainty_score":0.01032656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03184918215216552,"score_gpt":0.2321134373770681,"score_spread":0.2002642552249025,"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."}}