{"id":"W4366371937","doi":"10.1016/j.patrec.2023.04.006","title":"Large-margin representation learning for texture classification","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Margin (machine learning); Pattern recognition (psychology); Artificial intelligence; Computer science; Representation (politics); Convolutional neural network; CLs upper limits; Backpropagation; Metric (unit); Similarity (geometry); Feature learning; Artificial neural network; Machine learning; Image (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":[0.0003851427,0.0001211954,0.0001046173,0.0002561153,0.0002460298,0.0001543812,0.0002483125,0.00007157434,0.00003389873],"category_scores_gemma":[0.0000981498,0.0001360605,0.00008674016,0.0006460896,0.00001689434,0.0005905044,0.00006018847,0.0001768084,0.0006392623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009770348,"about_ca_system_score_gemma":0.00001374873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001150507,"about_ca_topic_score_gemma":0.000009207673,"domain_scores_codex":[0.9986266,0.000116599,0.0002261423,0.0004806879,0.0002454548,0.000304459],"domain_scores_gemma":[0.9992188,0.0002013867,0.0001678798,0.0002626456,0.0001003282,0.00004902653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001256224,0.00001960623,0.004224201,0.00005068189,0.00002358795,0.000004855777,0.001005377,0.000513157,0.01903755,0.00004101002,0.02040225,0.9546652],"study_design_scores_gemma":[0.001283475,0.00009692515,0.05097318,0.00008031273,0.00002324778,0.00001503107,0.0004440744,0.9159099,0.007177922,0.00220117,0.02131546,0.0004792575],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05326971,0.000005873206,0.9325463,0.01203958,0.0008430793,0.0004021481,0.00001278128,0.0007446816,0.0001359152],"genre_scores_gemma":[0.9935586,0.00002434308,0.001856592,0.003103508,0.0004098752,0.0004811129,0.0004020438,0.00002654158,0.0001373855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9541859,"threshold_uncertainty_score":0.8216637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06300581101001862,"score_gpt":0.3041775677600257,"score_spread":0.2411717567500071,"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."}}