{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000151113,0.0001298481,0.0001081548,0.00007277985,0.0005470227,0.00006697143,0.0004702695,0.00002942973,0.0001708425],"category_scores_gemma":[0.000006968635,0.0001146981,0.00004099804,0.0005272884,0.00003228117,0.0001482696,0.0003996469,0.0008409831,0.00003820454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004772585,"about_ca_system_score_gemma":0.000008994073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008050819,"about_ca_topic_score_gemma":0.000007643485,"domain_scores_codex":[0.9985019,0.000263437,0.0001380684,0.0004561978,0.0002968893,0.0003435043],"domain_scores_gemma":[0.9993933,0.00015069,0.00007407199,0.0002565414,0.00004416867,0.00008123586],"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":[0.00001243577,0.0000319403,0.001430352,0.000001976994,0.000004452336,0.00005791418,0.0001270322,0.3898437,0.0001118698,0.00001665285,0.00002592308,0.6083357],"study_design_scores_gemma":[0.0003695539,0.0005640296,0.004084513,0.000006463479,0.000007192569,0.000756108,0.00007832238,0.9918987,0.0001382867,0.001127281,0.0006911257,0.0002783935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.18919,0.00003307825,0.8091799,0.0008516153,0.00007459283,0.0002234676,0.000002903282,0.0002560595,0.0001883462],"genre_scores_gemma":[0.9862046,0.000008348344,0.01217781,0.001049259,0.0001203619,0.0002839811,0.0001021078,0.00001671459,0.000036881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7970145,"threshold_uncertainty_score":0.4677253,"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."}}