{"id":"W2135306627","doi":"10.5555/2503308.2503324","title":"Nonparametric guidance of autoencoder representations using label information","year":2012,"lang":"en","type":"article","venue":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; University of Toronto","funders":"","keywords":"Discriminative model; Autoencoder; Artificial intelligence; Computer science; Machine learning; Nonparametric statistics; Pattern recognition (psychology); Unsupervised learning; Feature learning; Representation (politics); Artificial neural network; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0002831683,0.0002250503,0.0002507258,0.001363081,0.0003647041,0.001129349,0.001382939,0.0001220403,0.0002215509],"category_scores_gemma":[0.0003234214,0.0002603638,0.0001365988,0.002902901,0.00006143204,0.03872323,0.001047732,0.0002227548,0.002479701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003524527,"about_ca_system_score_gemma":0.0001005445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002960152,"about_ca_topic_score_gemma":0.000007032975,"domain_scores_codex":[0.9981446,0.00008903258,0.0004082905,0.0003313709,0.0005476209,0.0004791151],"domain_scores_gemma":[0.9980632,0.0001270616,0.0003494851,0.0005758191,0.0005182638,0.0003661497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004453289,0.002108305,0.7447786,0.0004495574,0.0006034801,0.00008174883,0.004697896,0.006742251,0.006210196,0.09821981,0.008160166,0.1275026],"study_design_scores_gemma":[0.002810309,0.0002342103,0.3888356,0.0003180171,0.0001591523,0.00008738623,0.0003114775,0.01267193,0.02820428,0.001499269,0.563094,0.001774395],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7070178,0.000007950695,0.2559376,0.00008854499,0.0004851438,0.0004600163,0.0001441284,0.0002761745,0.03558265],"genre_scores_gemma":[0.9882,0.00000995495,0.01024909,0.0004050547,0.00006540192,0.000003029973,0.00006705747,0.00001350181,0.0009868988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5549338,"threshold_uncertainty_score":0.9999849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05511407328358745,"score_gpt":0.290306662466673,"score_spread":0.2351925891830855,"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."}}