{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00153244,0.001178252,0.001097729,0.0006797878,0.0005054448,0.001038833,0.002102414,0.001601815,0.01118237],"category_scores_gemma":[0.00409126,0.0006002448,0.00082372,0.0009015138,0.0003899509,0.00218293,0.002145373,0.003130873,0.008801141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004125129,"about_ca_system_score_gemma":0.001066479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003282546,"about_ca_topic_score_gemma":0.006592023,"domain_scores_codex":[0.9990471,0.000310387,0.00006007722,0.0002286928,0.0002694874,0.00008424267],"domain_scores_gemma":[0.9986731,0.0005533071,0.00005318428,0.0003165424,0.0003246639,0.00007922002],"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":[0.0004510932,0.0002151121,0.0004508576,0.0001301277,0.00008420063,0.00007647788,0.00005280742,0.03457623,0.01461095,0.0111062,0.02593544,0.9123105],"study_design_scores_gemma":[0.0000428502,0.0001030233,0.0003127971,0.00003864406,0.00002626344,0.00007934171,0.00002082017,0.9573479,0.0157922,0.01346154,0.01274587,0.00002877584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004424834,0.0007964427,0.9864402,0.0002653794,0.0002260513,0.00005922844,0.0005681762,0.005881602,0.001338029],"genre_scores_gemma":[0.1301541,0.0008165929,0.8403043,0.0008982231,0.0003232702,0.0003748038,0.003273398,0.0009517975,0.02290351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01118237,"threshold_uncertainty_score":0.03740877,"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."}}