{"id":"W3002486569","doi":"10.48550/arxiv.2001.07766","title":"Adaptive Loss Function for Super Resolution Neural Networks Using Convex Optimization Techniques","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Task (project management); Image (mathematics); Process (computing); Function (biology); Pattern recognition (psychology); Pixel; Resolution (logic); Image resolution; Regular polygon; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002446637,0.00161138,0.001161837,0.000687435,0.0003180611,0.001018967,0.001459636,0.001654306,0.002352201],"category_scores_gemma":[0.005728323,0.0006826148,0.0008182614,0.0006742072,0.001224357,0.001696263,0.001940687,0.003346443,0.0008215647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001455502,"about_ca_system_score_gemma":0.001035877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002886293,"about_ca_topic_score_gemma":0.002774653,"domain_scores_codex":[0.9991487,0.0003533762,0.00003651819,0.0001376826,0.0002560324,0.00006759842],"domain_scores_gemma":[0.9982133,0.001233514,0.0001394519,0.0001093532,0.0002451106,0.00005932423],"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":[0.00005806684,0.00003881848,0.0002075592,0.00009006125,0.00004169833,0.00009056667,0.00003757607,0.925644,0.00302783,0.03308202,0.002879357,0.03480247],"study_design_scores_gemma":[0.000001778492,0.000004763512,0.00002019605,0.000003754147,0.000001391304,0.000009391086,0.000001459843,0.9950074,0.0002289019,0.004500475,0.0002187431,0.00000183047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0022522,0.0002732968,0.9959906,0.0002307883,0.00001988985,0.00002182836,0.00003320751,0.0001421315,0.00103606],"genre_scores_gemma":[0.3853711,0.001723276,0.5951489,0.0007152361,0.0002473508,0.0007372999,0.0006523861,0.0008633015,0.01454114],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002886293,"threshold_uncertainty_score":0.01293921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1048015478455942,"score_gpt":0.2208386456457234,"score_spread":0.1160370978001292,"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."}}