{"id":"W2621841016","doi":"10.1016/j.sigpro.2017.05.030","title":"LMAE: A large margin Auto-Encoders for classification","year":2017,"lang":"en","type":"article","venue":"Signal Processing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"China University of Petroleum, Beijing; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Softmax function; MNIST database; Encoder; Pattern recognition (psychology); Computer science; Artificial intelligence; Classifier (UML); Discriminative model; Margin (machine learning); Artificial neural network; Feature learning; Deep learning; Autoencoder; Algorithm; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006877187,0.0001158033,0.000114711,0.00007026997,0.001418317,0.001152396,0.001117195,0.00006855019,0.00000978836],"category_scores_gemma":[0.0001864699,0.0001075357,0.00004639742,0.00008249648,0.00004995008,0.001358848,0.000129591,0.0001460056,0.00003504761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003461256,"about_ca_system_score_gemma":0.0001458634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001270143,"about_ca_topic_score_gemma":0.000005386656,"domain_scores_codex":[0.998848,0.00003717271,0.0001888669,0.0004322707,0.0002099194,0.0002837658],"domain_scores_gemma":[0.9987513,0.00005237565,0.0003436639,0.0006530613,0.0001279298,0.00007166366],"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":[0.00001590966,0.00006606204,0.002432544,0.0001238033,0.000006646917,0.000001441156,0.0005004758,0.00002116709,0.007799324,0.04809588,0.001553356,0.9393834],"study_design_scores_gemma":[0.0003836874,0.00003110251,0.01612448,0.00005281062,0.000006861659,0.000003405172,0.00005740832,0.9424575,0.0003248018,0.004744879,0.03565149,0.0001615671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006001952,0.0001059269,0.9898573,0.004701591,0.0001066758,0.0001720712,0.000006545629,0.0002052796,0.004244431],"genre_scores_gemma":[0.9501281,0.000003583271,0.04878593,0.0001818608,0.0001292786,0.00005077637,0.000030847,0.0000116297,0.0006779748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9495279,"threshold_uncertainty_score":0.9998845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04834297452391868,"score_gpt":0.3301413279254549,"score_spread":0.2817983534015362,"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."}}