{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003217108,0.0001198776,0.00034401,0.0002572157,0.00004234544,0.0000757436,0.000381174,0.00005916717,0.00002065053],"category_scores_gemma":[0.00008306176,0.00008563333,0.0001291311,0.0007183505,0.00002867766,0.0003123774,0.00007730137,0.00009359825,0.000001098466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003036574,"about_ca_system_score_gemma":0.00004771187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000751653,"about_ca_topic_score_gemma":0.000403131,"domain_scores_codex":[0.9989291,0.0001807878,0.0001905895,0.0003017359,0.0001938839,0.000203905],"domain_scores_gemma":[0.9992638,0.0001249904,0.00006060481,0.0002902376,0.0001466308,0.0001137926],"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":[0.00006819358,0.0003688665,0.1561865,0.00001157863,0.0003759039,0.0000042111,0.00602906,0.8182407,0.001375121,0.00204994,0.002724574,0.01256541],"study_design_scores_gemma":[0.0003278033,0.0001576868,0.0414912,0.000003874155,0.0000669795,2.078003e-7,0.0003265377,0.955898,0.0009679188,0.0002963237,0.0003542762,0.0001091283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1105885,0.00004801239,0.8880842,0.0007385046,0.00007721783,0.0001124022,0.000001551467,0.00003618198,0.0003133875],"genre_scores_gemma":[0.9082458,0.000003756813,0.09118143,0.0001297283,0.00003719602,0.00001136237,0.00001021721,0.000004829481,0.0003756582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7976573,"threshold_uncertainty_score":0.3492026,"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."}}