{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000204133,0.0003723025,0.0003576467,0.0002366822,0.000338877,0.0001812002,0.001083721,0.0004084509,0.000003964019],"category_scores_gemma":[0.00005973094,0.0004640794,0.0001819557,0.0006420464,0.0001544559,0.001336458,0.001373482,0.0005901415,0.000001214925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004146151,"about_ca_system_score_gemma":0.0001476831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003539273,"about_ca_topic_score_gemma":0.000002860144,"domain_scores_codex":[0.9978704,0.0001275659,0.0002592554,0.001273944,0.00009565622,0.0003731973],"domain_scores_gemma":[0.9981822,0.00008056963,0.000397779,0.0007049209,0.0005150763,0.0001194646],"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":[0.0001448863,0.00002881371,0.00006413318,0.00005581982,0.00003246148,0.00002870201,0.00005416451,0.9803941,0.000130688,0.01758778,0.0001285988,0.001349824],"study_design_scores_gemma":[0.0002006597,0.0001515553,0.00001081108,0.0001069292,0.00008239945,0.000005489961,0.00001967736,0.9533561,0.0004123338,0.04513556,0.00007810594,0.000440418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004436794,0.000101748,0.9962986,0.0001351309,0.0003781327,0.0008327427,0.00001180518,0.001695601,0.0001025309],"genre_scores_gemma":[0.5289878,0.00005138598,0.4705759,0.0001523585,0.0001285488,0.000006003658,0.00003393243,0.00002918376,0.00003494399],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5285441,"threshold_uncertainty_score":0.9997811,"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."}}