{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004556127,0.0001330506,0.0001949059,0.0001849905,0.0001711834,0.00005862419,0.0005349602,0.00007124793,0.00006360929],"category_scores_gemma":[0.00007856813,0.0001470786,0.0002072271,0.0005103545,0.00005455073,0.000393229,0.00008448772,0.00009685227,0.00009722902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005641989,"about_ca_system_score_gemma":0.00007225159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002669075,"about_ca_topic_score_gemma":0.00003305442,"domain_scores_codex":[0.9988517,0.0001242259,0.0001256205,0.0005212897,0.00006954658,0.0003076429],"domain_scores_gemma":[0.9990525,0.0002605319,0.00009438445,0.0003105314,0.0001232989,0.0001587201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001877271,0.00008126652,0.0002532588,0.00001620839,0.0001380741,0.00001870782,0.0005136752,0.07587193,0.0003522488,0.907425,0.001397057,0.01391379],"study_design_scores_gemma":[0.0006773591,0.00005013532,0.0001408375,0.000009526197,0.00005157594,0.00000514707,0.0001505314,0.9550141,0.00007573531,0.02994873,0.0136823,0.0001940573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005027005,0.000006988621,0.9909393,0.0005619674,0.0001265764,0.00009205389,0.000006817037,0.0001698948,0.003069367],"genre_scores_gemma":[0.8629659,0.000006884567,0.1342051,0.0008095789,0.00005233671,0.000001045452,0.00001070046,0.000007540287,0.00194092],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8791422,"threshold_uncertainty_score":0.5997692,"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."}}