{"id":"W3165895193","doi":"10.1016/j.patcog.2022.108893","title":"Learning deep morphological networks with neural architecture search","year":2022,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Pooling; Computer science; Artificial intelligence; Salient; Segmentation; Deep learning; Representation (politics); Pattern recognition (psychology); Linear map; Feature (linguistics); Artificial neural network; Mathematical morphology; Deep neural networks; Image processing; Image (mathematics); 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":[0.0005915355,0.0008912983,0.0009638443,0.0008198993,0.0004190397,0.0009098216,0.00145279,0.001950116,0.00764098],"category_scores_gemma":[0.002026573,0.0008874324,0.0009651998,0.0008879298,0.0006728477,0.001582282,0.001698768,0.001647514,0.001778145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006447505,"about_ca_system_score_gemma":0.000959182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002262087,"about_ca_topic_score_gemma":0.004596669,"domain_scores_codex":[0.9998019,0.0000337358,0.00001516568,0.00006435627,0.00005064686,0.00003417219],"domain_scores_gemma":[0.9994184,0.0002585341,0.00006436798,0.00008417654,0.0001313193,0.00004335956],"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":[0.00025151,0.0001041307,0.001509732,0.0001618658,0.00009292061,0.000185411,0.00005446811,0.5036709,0.0104314,0.02236903,0.006130811,0.4550377],"study_design_scores_gemma":[0.00001164241,0.00003317232,0.00006639303,0.00001096693,0.00001028992,0.00002291975,0.000007842091,0.9917065,0.001171529,0.006414425,0.0005404656,0.000003793055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04506435,0.0005558294,0.9459151,0.0005065675,0.00016584,0.00006370067,0.0001832422,0.002017404,0.005528007],"genre_scores_gemma":[0.4730476,0.0004120189,0.5115466,0.0005732905,0.000117846,0.0001799196,0.0005806989,0.0004177628,0.01312421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00764098,"threshold_uncertainty_score":0.02556163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02513212554938399,"score_gpt":0.2462412908652323,"score_spread":0.2211091653158483,"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."}}