{"id":"W2962876041","doi":"","title":"An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family","year":2016,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Softmax function; Probabilistic logic; Function (biology); Categorical variable; MNIST database; Computer science; Range (aeronautics); Mathematics; Algorithm; Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Discrete mathematics; Machine learning; Engineering","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":[0.0002469793,0.00009657998,0.00009297267,0.0001183021,0.0001342514,0.0001545977,0.001068131,0.00002638479,0.00007527637],"category_scores_gemma":[0.0003615372,0.00006391116,0.00004428669,0.0001782813,0.00005252846,0.00133356,0.000146668,0.0001232433,0.00008730679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000473758,"about_ca_system_score_gemma":0.00006599554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008961965,"about_ca_topic_score_gemma":0.00001971111,"domain_scores_codex":[0.9985802,0.0001492535,0.0002639621,0.0003689985,0.0004962398,0.0001413728],"domain_scores_gemma":[0.9987567,0.000252541,0.0001431905,0.0004138473,0.0003654039,0.00006833099],"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":[0.00002464052,0.00009173237,0.01097644,0.00000202764,0.00004214205,0.000007061269,0.007217684,0.04341233,0.03243806,0.7676459,0.00009066498,0.1380513],"study_design_scores_gemma":[0.001072137,0.0005702073,0.05795035,0.0003154335,0.00001321648,0.00001479631,0.004116753,0.8480596,0.01568765,0.06769388,0.003925782,0.0005801721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1158389,0.000002784511,0.862653,0.01672734,0.0003365822,0.000111796,0.000003238653,0.00008056028,0.004245845],"genre_scores_gemma":[0.9830117,0.00001620272,0.01576108,0.0001848437,0.0001238532,0.00004348687,0.000004059839,0.000007296859,0.0008474843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8671728,"threshold_uncertainty_score":0.2606221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1042967105268677,"score_gpt":0.3749509464872322,"score_spread":0.2706542359603645,"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."}}