{"id":"W2744909235","doi":"10.1016/j.neunet.2014.09.005","title":"Challenges in representation learning: A report on three machine learning contests","year":2014,"lang":"en","type":"article","venue":"Neural Networks","topic":"Topic Modeling","field":"Computer Science","cited_by":676,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Toronto; Université de Montréal","funders":"","keywords":"Computer science; Representation (politics); Artificial intelligence; Learning to learn; Feature learning; Machine learning; Mathematics education; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0006144415,0.0001301689,0.0001855015,0.00007952236,0.0000871722,0.00007324638,0.000343226,0.00008019137,0.000003145375],"category_scores_gemma":[0.0003460436,0.0001221898,0.00004594608,0.0001719917,0.00001491108,0.0002112414,0.000150488,0.0006556227,0.000007056291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002475058,"about_ca_system_score_gemma":0.000006460659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006786645,"about_ca_topic_score_gemma":0.0003858974,"domain_scores_codex":[0.9984179,0.000226255,0.0002913612,0.0005523593,0.0002305856,0.0002814977],"domain_scores_gemma":[0.9989905,0.0002876694,0.0001566452,0.0004699576,0.00003415188,0.00006103532],"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":[0.000007137201,0.00001236979,0.04595502,0.000002843898,0.000002152008,0.00007558255,0.0001294615,0.6221628,0.000009898873,0.003880547,0.000009214436,0.3277529],"study_design_scores_gemma":[0.0002637584,0.0001256665,0.02849583,0.00002968001,0.000001355133,0.00006939829,0.000007092927,0.9690793,0.000009936835,0.0007947084,0.001007022,0.0001162951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2017872,0.0009344963,0.7801663,0.004447049,0.0008267298,0.0002449321,2.939139e-8,0.0004842367,0.011109],"genre_scores_gemma":[0.9979354,0.00007591283,0.00136187,0.0001497248,0.0002488069,0.00001272446,0.000003597356,0.0000122323,0.0001997113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7961482,"threshold_uncertainty_score":0.4982754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07473609516329448,"score_gpt":0.2917676883922016,"score_spread":0.2170315932289071,"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."}}