{"id":"W193255932","doi":"10.1007/978-3-642-42054-2_41","title":"Semi Supervised Autoencoders: Better Focusing Model Capacity during Feature Extraction","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Autoencoder; Artificial intelligence; Pattern recognition (psychology); Machine learning; Feature extraction; Task (project management); Unsupervised learning; Deep learning; Data mining","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005137195,0.0007309941,0.0006206019,0.0006292965,0.0005940425,0.001197692,0.002268847,0.0005298323,0.00005054632],"category_scores_gemma":[0.0000616313,0.0006612116,0.000225096,0.0004635475,0.0004839363,0.002289259,0.0009643081,0.001277529,0.00005730498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004653509,"about_ca_system_score_gemma":0.0003144812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004572361,"about_ca_topic_score_gemma":0.00006387235,"domain_scores_codex":[0.9957175,0.00006345718,0.0004744855,0.001860308,0.000982563,0.0009016569],"domain_scores_gemma":[0.9975045,0.0002261286,0.0003055848,0.001391953,0.0003432498,0.0002286373],"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":[0.000005083651,0.00002592256,0.00002207614,0.00004293257,0.00002255323,0.00004197894,0.0008781062,0.8282987,0.006411985,0.000812517,0.0002175438,0.1632206],"study_design_scores_gemma":[0.0002211856,0.0000379614,0.00009343671,0.0002822571,0.00001257325,0.0000531991,2.162691e-7,0.9570409,0.008613462,0.03269477,0.0002286866,0.0007213398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008307414,0.0002101048,0.9927414,0.002046879,0.001498686,0.0004454419,0.000005437232,0.0002011656,0.002020139],"genre_scores_gemma":[0.1630374,0.00003535975,0.8335765,0.001258218,0.001108308,0.00001372066,0.000004067947,0.00005037586,0.0009160761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1624992,"threshold_uncertainty_score":0.9998392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02212003609481173,"score_gpt":0.2262780331622139,"score_spread":0.2041579970674021,"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."}}