{"id":"W4285241469","doi":"10.1109/tai.2022.3177394","title":"Nonoverlapping Feature Projection Convolutional Neural Network With Differentiable Loss Function","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Feature (linguistics); Differentiable function; Convolution (computer science); Computer science; Pattern recognition (psychology); Pixel; Artificial intelligence; Feature vector; Convolutional neural network; Projection (relational algebra); Separable space; Algorithm; Function (biology); Mathematics; Artificial neural network; 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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0001607732,0.000245096,0.0001777327,0.0001597062,0.001861885,0.0001297542,0.0005621676,0.000058315,0.0001650803],"category_scores_gemma":[0.000002135102,0.0002437505,0.0001032658,0.001794625,0.0001112528,0.0005264571,0.00001478319,0.000772342,0.00006142051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002293053,"about_ca_system_score_gemma":0.0000871446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002479276,"about_ca_topic_score_gemma":0.00009237651,"domain_scores_codex":[0.997867,0.0001254849,0.000307105,0.0006993613,0.0005254984,0.0004755875],"domain_scores_gemma":[0.9989398,0.0001539551,0.0001556171,0.0005330538,0.0001140609,0.0001035338],"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":[0.0001879601,0.0002185811,0.00001402605,0.000004140336,0.00002650135,0.000005046259,0.00008890695,0.9271175,0.0007130342,0.01991887,0.0002934334,0.05141195],"study_design_scores_gemma":[0.0000862395,0.0006807544,0.0001336519,0.00001640473,0.00003421264,0.0001192179,0.0001320659,0.9727252,0.007255034,0.01438688,0.003999208,0.0004311714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00704037,0.00003558531,0.9891388,0.001219453,0.001406639,0.0005631671,0.00001660324,0.0004194996,0.0001598774],"genre_scores_gemma":[0.9882467,0.00001035795,0.009792364,0.000476919,0.0001977203,0.000567382,0.000009539401,0.00002470892,0.0006743294],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9812063,"threshold_uncertainty_score":0.9994376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03097946788488648,"score_gpt":0.2552014065410654,"score_spread":0.224221938656179,"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."}}