{"id":"W2952342326","doi":"","title":"Winner-Take-All Autoencoders","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Autoencoder; Computer science; Artificial intelligence; Pattern recognition (psychology); Winner-take-all; Deep learning; Convolutional neural network; Feature (linguistics); Layer (electronics); Face (sociological concept); Feature learning; Unsupervised learning; Invariant (physics); Machine learning; Artificial neural network; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001738855,0.001612336,0.001965535,0.0005237554,0.0005745589,0.001059276,0.003068731,0.001639014,0.004050889],"category_scores_gemma":[0.0036893,0.0008812727,0.001215289,0.0006507666,0.00110304,0.002003277,0.001868568,0.002263154,0.001717398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007124983,"about_ca_system_score_gemma":0.001342443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003055883,"about_ca_topic_score_gemma":0.00577496,"domain_scores_codex":[0.998953,0.0002563969,0.00006613539,0.0002639582,0.0003084504,0.0001520672],"domain_scores_gemma":[0.9989591,0.0003796078,0.00008779453,0.0002830779,0.0002260249,0.00006447844],"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":[0.000339846,0.0003463676,0.001444465,0.0002377172,0.0004086888,0.0002036732,0.0001547687,0.4875773,0.009707664,0.03195435,0.0125844,0.4550408],"study_design_scores_gemma":[0.00001725464,0.00004694554,0.0001589409,0.000007936004,0.0000200578,0.00003858521,0.00001228756,0.9851783,0.002604012,0.01087168,0.001033331,0.00001061035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01604686,0.0004285094,0.9783237,0.0002878262,0.0001085352,0.00008918294,0.0001394293,0.001777597,0.002798259],"genre_scores_gemma":[0.6307588,0.000547026,0.3460912,0.0008979173,0.0002220134,0.0003599171,0.001027929,0.0004365495,0.01965865],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004050889,"threshold_uncertainty_score":0.01355153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1126037527016249,"score_gpt":0.2184972110772711,"score_spread":0.1058934583756461,"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."}}