{"id":"W1793338510","doi":"","title":"A Winner-Take-All Method for Training Sparse Convolutional Autoencoders.","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Face recognition and analysis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"MNIST database; Autoencoder; Computer science; Artificial intelligence; Winner-take-all; Convolutional neural network; Pattern recognition (psychology); Deep learning; Feature (linguistics); Machine learning; Feature learning; Face (sociological concept); Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.00133151,0.001367618,0.001254805,0.0006139062,0.0005027223,0.0006900033,0.002206834,0.001500146,0.004552929],"category_scores_gemma":[0.00259759,0.000756607,0.001139811,0.0006244986,0.0006613179,0.001471134,0.001674505,0.001947874,0.001903313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005732971,"about_ca_system_score_gemma":0.001241154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00294138,"about_ca_topic_score_gemma":0.007477537,"domain_scores_codex":[0.9992981,0.0001736037,0.00004143403,0.0001601718,0.0002399631,0.00008675197],"domain_scores_gemma":[0.9993576,0.0002095509,0.00005272968,0.0001725298,0.0001531072,0.00005446288],"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":[0.0003349608,0.0003321295,0.001101235,0.0002565666,0.0004876413,0.0001922374,0.0001203418,0.2485132,0.01598473,0.02105879,0.01710989,0.6945083],"study_design_scores_gemma":[0.00003301803,0.00007497114,0.0001937074,0.000009960257,0.0000344773,0.00007779997,0.00001417913,0.9822354,0.005993694,0.00888487,0.002434403,0.00001346274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006979745,0.0002856939,0.9883232,0.0001569929,0.00008602666,0.0001098966,0.0001183283,0.002033904,0.001906321],"genre_scores_gemma":[0.3227972,0.0004590903,0.6547009,0.0005873787,0.0001597997,0.0004904129,0.001268246,0.0005619988,0.01897498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004552929,"threshold_uncertainty_score":0.01523107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1398785114593155,"score_gpt":0.2163937755837255,"score_spread":0.07651526412440995,"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."}}