{"id":"W2343086953","doi":"10.48550/arxiv.1604.08859","title":"The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Softmax function; Differentiable function; Computer science; Function (biology); Algorithm; Computation; Language model; Task (project management); Word (group theory); Scale (ratio); Artificial intelligence; Artificial neural network; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004114575,0.002786637,0.001726269,0.001249151,0.000521043,0.002585158,0.002590886,0.002412356,0.004504433],"category_scores_gemma":[0.009679646,0.0004660764,0.001492636,0.001591036,0.001865895,0.003884905,0.003107005,0.003903639,0.004330612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001646606,"about_ca_system_score_gemma":0.00187119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002883545,"about_ca_topic_score_gemma":0.002515833,"domain_scores_codex":[0.9975821,0.0007243267,0.0001925771,0.0004870929,0.0008164175,0.0001975566],"domain_scores_gemma":[0.9970283,0.001333911,0.0003094331,0.0005927639,0.0005954194,0.0001401941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008292551,0.0004188712,0.003629025,0.000414822,0.0002675814,0.0002760855,0.0001255271,0.3656446,0.01561854,0.04926578,0.05609115,0.5074188],"study_design_scores_gemma":[0.00003378985,0.0002201722,0.0009151999,0.0000412603,0.00002721948,0.000187861,0.00003367744,0.9645352,0.004268707,0.02386608,0.00583389,0.00003693762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01510502,0.001074389,0.9752617,0.001220855,0.00018936,0.0001223612,0.0005683566,0.002276583,0.004181344],"genre_scores_gemma":[0.5749303,0.003349968,0.3804092,0.003501985,0.0006100663,0.001023995,0.005473772,0.00194731,0.02875346],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004504433,"threshold_uncertainty_score":0.02176017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05429059800473403,"score_gpt":0.2043723561059911,"score_spread":0.1500817581012571,"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."}}