{"id":"W2100495367","doi":"10.1126/science.1127647","title":"Reducing the Dimensionality of Data with Neural Networks","year":2006,"lang":"en","type":"article","venue":"Science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":20953,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Autoencoder; Curse of dimensionality; Initialization; Gradient descent; Artificial neural network; Computer science; Principal component analysis; Artificial intelligence; Pattern recognition (psychology); Layer (electronics); High dimensional; Principal (computer security); Algorithm; Materials science; Nanotechnology","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":[0.00184146,0.001352217,0.001462141,0.00133982,0.0007345267,0.002154894,0.001149988,0.001273694,0.001775509],"category_scores_gemma":[0.01410888,0.0008932269,0.001176584,0.001864302,0.001395105,0.00465274,0.003225147,0.003590527,0.001229784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000821901,"about_ca_system_score_gemma":0.001113067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002311958,"about_ca_topic_score_gemma":0.002694622,"domain_scores_codex":[0.9978896,0.0005711495,0.000216713,0.0003664195,0.0008588225,0.00009720357],"domain_scores_gemma":[0.9963118,0.001802654,0.0002146634,0.001083549,0.0005181376,0.00006916805],"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":[0.0002555628,0.000148212,0.002491978,0.0007146577,0.0003368478,0.0002201385,0.0004290793,0.2951956,0.01777397,0.06710158,0.01442049,0.6009119],"study_design_scores_gemma":[0.00002238203,0.00004703479,0.0006714924,0.00006663339,0.00004416724,0.0000935651,0.0000744223,0.8408451,0.008794585,0.138428,0.01087136,0.00004133062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008521799,0.001175131,0.9870107,0.0008149627,0.0001230324,0.00004798942,0.0002043347,0.0008380173,0.001263918],"genre_scores_gemma":[0.1597928,0.002935888,0.8319172,0.0005873636,0.0003544378,0.0003259787,0.001144295,0.000277384,0.002664616],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002311958,"threshold_uncertainty_score":0.009738684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02973157325527122,"score_gpt":0.276790050995563,"score_spread":0.2470584777402918,"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."}}