{"id":"W2145836866","doi":"10.1109/ccece.2008.4564577","title":"Reconstruction of handwritten digit images using autoencoder neural networks","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Autoencoder; Restricted Boltzmann machine; Artificial intelligence; Computer science; Pattern recognition (psychology); Artificial neural network; Numerical digit; Deep learning; Iterative reconstruction; Mathematics; Arithmetic","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0008546216,0.000714306,0.0005653918,0.0004317276,0.0001363492,0.0005257173,0.000470751,0.0006357669,0.001378783],"category_scores_gemma":[0.002531501,0.0004140903,0.0005612752,0.0003898537,0.0003533995,0.0008387439,0.0004565008,0.000799111,0.0004481712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004142042,"about_ca_system_score_gemma":0.0004006661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002374942,"about_ca_topic_score_gemma":0.002873898,"domain_scores_codex":[0.9996978,0.00007653786,0.00001801397,0.00006582326,0.0001088771,0.0000329221],"domain_scores_gemma":[0.9991068,0.0005083858,0.00007891804,0.0001352667,0.0001524857,0.00001803807],"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":[0.0002549314,0.00005363657,0.0009579058,0.00008896713,0.0000923599,0.0001063114,0.00004130098,0.7892635,0.02531334,0.002101656,0.0005841992,0.1811418],"study_design_scores_gemma":[0.000003274962,0.00001865881,0.000339323,0.000005605399,0.000007372853,0.00003358118,0.000005149713,0.9872488,0.01159622,0.0005490181,0.0001866734,0.000006231474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1255333,0.0005030763,0.8698156,0.0001368978,0.00006920398,0.00004028245,0.000102666,0.001575987,0.00222309],"genre_scores_gemma":[0.708314,0.0003875605,0.2873589,0.00009715817,0.00002105745,0.00003527767,0.0002823449,0.00009705446,0.003406597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002374942,"threshold_uncertainty_score":0.004722238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01945401360421767,"score_gpt":0.1903344477997712,"score_spread":0.1708804341955535,"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."}}