{"id":"W1659448245","doi":"10.1109/ijcnn.2015.7280568","title":"An empirical analysis of different sparse penalties for autoencoder in unsupervised feature learning","year":2015,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; MNIST database; Computer science; Feature learning; Sparse approximation; Artificial intelligence; Machine learning; Pattern recognition (psychology); Representation (politics); Feature (linguistics); Feature vector; Norm (philosophy); Matrix norm; Deep learning","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":[0.0168003,0.001232199,0.001027212,0.001715373,0.0008447318,0.001190505,0.001263534,0.001669102,0.001286187],"category_scores_gemma":[0.07964677,0.0004426221,0.0008818713,0.001610268,0.002285317,0.004130593,0.002185523,0.002771842,0.0002850441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001373551,"about_ca_system_score_gemma":0.001129773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001682423,"about_ca_topic_score_gemma":0.002649714,"domain_scores_codex":[0.9940742,0.002681714,0.0004159951,0.000893709,0.001627344,0.0003070719],"domain_scores_gemma":[0.9154574,0.06861233,0.002966323,0.007406694,0.004706096,0.0008512634],"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":[0.0013114,0.0005636519,0.03618613,0.0009724131,0.000522409,0.0003482338,0.0003949508,0.5981804,0.007758545,0.05303281,0.007777572,0.2929515],"study_design_scores_gemma":[0.00004111416,0.0003767363,0.009856503,0.0001321213,0.00006805005,0.0004822146,0.0001319501,0.9594237,0.00669046,0.02111859,0.001622098,0.00005645746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3240201,0.005937706,0.6625548,0.001286407,0.0001275584,0.0002000519,0.0005688695,0.0009822057,0.004322359],"genre_scores_gemma":[0.8764138,0.001548809,0.1178956,0.0002098129,0.0000774357,0.0002314073,0.001835568,0.0003654138,0.001422263],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0168003,"threshold_uncertainty_score":0.08884954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05290945777520761,"score_gpt":0.3123700623296399,"score_spread":0.2594606045544323,"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."}}