{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000908848,0.0004190625,0.0005011711,0.000292409,0.0001517169,0.000215933,0.002982963,0.0004024004,0.00002926557],"category_scores_gemma":[0.00008948131,0.0004755156,0.0003384041,0.0005140722,0.0001270912,0.0003594149,0.001842245,0.0008031855,0.0002577561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001588077,"about_ca_system_score_gemma":0.0002145742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001609977,"about_ca_topic_score_gemma":0.0000564055,"domain_scores_codex":[0.9970639,0.0004694189,0.0002534483,0.001506034,0.0001431761,0.0005640695],"domain_scores_gemma":[0.9968735,0.0002540729,0.0003159906,0.002160073,0.0001595296,0.0002368105],"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":[0.00002628329,0.0001332567,0.007570419,0.0001710756,0.0002861363,0.0006565733,0.0004972609,0.7069651,0.00003714968,0.2716724,0.003093833,0.008890464],"study_design_scores_gemma":[0.0005244177,0.00006502827,0.004308799,0.00009750463,0.00006053116,0.00001067908,0.00002108133,0.8584596,0.00009505427,0.1214497,0.0140473,0.000860323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04145178,0.00006279329,0.9465634,0.0003285328,0.001572814,0.0001866034,0.000006166546,0.0006600016,0.009167917],"genre_scores_gemma":[0.9684141,0.0001085278,0.02912283,0.0005421001,0.0001614787,8.912924e-7,0.00001339061,0.0000274213,0.001609216],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9269624,"threshold_uncertainty_score":0.9997696,"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."}}