{"id":"W4225274980","doi":"10.7717/peerj-cs.951","title":"Deep learning methods for inverse problems","year":2022,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inverse problem; Outlier; Computer science; Robustness (evolution); Artificial intelligence; Inverse; Rendering (computer graphics); Machine learning; Pattern recognition (psychology); Mathematical optimization; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007293797,0.00008555115,0.0001006576,0.0001401067,0.0004256082,0.0000802364,0.0004555346,0.00001253177,0.00001380038],"category_scores_gemma":[0.00002057631,0.00009120041,0.00004043649,0.0004385208,0.00007790313,0.0001397991,0.000309071,0.0001672154,0.000002563125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000739625,"about_ca_system_score_gemma":0.00002081792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006186279,"about_ca_topic_score_gemma":9.227273e-7,"domain_scores_codex":[0.99918,0.00004012802,0.0001053259,0.0002294428,0.0001820915,0.0002629677],"domain_scores_gemma":[0.9995936,0.00007132655,0.00002390967,0.000193454,0.00006401355,0.00005372068],"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":[0.000001024299,0.000006937903,0.00003597106,0.000006667286,0.000004098144,0.00000123156,0.0005358555,0.7799267,0.01663623,0.0004801459,0.0009220081,0.2014431],"study_design_scores_gemma":[0.00006866067,0.00007067496,0.00007372699,0.000004761402,0.000002965888,0.00001495908,0.00001640229,0.9457094,0.008429709,0.001792487,0.04369605,0.0001201986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007565645,0.0001122835,0.9900901,0.00005149714,0.0007105451,0.000164768,3.85108e-7,0.0007940101,0.0005107822],"genre_scores_gemma":[0.3004906,0.000004032941,0.6992118,0.0001163026,0.00006215626,0.00005361087,0.000001371797,0.000013602,0.00004651777],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2929249,"threshold_uncertainty_score":0.3719045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02891769631331021,"score_gpt":0.2974497916580822,"score_spread":0.268532095344772,"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."}}