{"id":"W2980025636","doi":"10.1007/978-3-030-32520-6_22","title":"Negative Log Likelihood Ratio Loss for Deep Neural Network Classification","year":2019,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Huawei Technologies (Canada)","funders":"","keywords":"Discriminative model; Cross entropy; Pattern recognition (psychology); Artificial intelligence; Artificial neural network; Generative grammar; Entropy (arrow of time); Mathematics; Contextual image classification; Computer science; Deep neural networks; Image (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"],"consensus_categories":[],"category_scores_codex":[0.0003439439,0.0004845418,0.0006560556,0.0001412051,0.0002709577,0.000193761,0.0007978331,0.0002335683,0.000002266038],"category_scores_gemma":[0.00002971504,0.0004809551,0.0001272524,0.0001695566,0.0001047483,0.0005293329,0.000328319,0.0004486605,0.00002901934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001652908,"about_ca_system_score_gemma":0.00005039161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006080061,"about_ca_topic_score_gemma":0.00004156863,"domain_scores_codex":[0.9970201,0.00005381529,0.0009869187,0.001104873,0.0002718037,0.0005624623],"domain_scores_gemma":[0.9968544,0.001193993,0.000909107,0.0007225763,0.0002111856,0.0001086962],"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":[0.000009723903,0.000009486699,0.0001032737,0.0001302709,0.00001767892,0.000002714547,0.0001464038,0.1889633,0.000003027156,0.6638198,0.00006210722,0.1467322],"study_design_scores_gemma":[0.0001979695,0.0001093568,0.00003569794,0.0005216788,0.00001444147,0.00002779782,0.00006027374,0.8618449,0.00001289316,0.07811071,0.05855687,0.0005074226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003559381,0.01668912,0.9648261,0.0001307302,0.002025607,0.002019087,0.000009112463,0.0001453042,0.01411931],"genre_scores_gemma":[0.8475347,0.01065406,0.1073609,0.0008442058,0.005035988,0.0005932169,0.0001943352,0.0003286392,0.02745401],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8574653,"threshold_uncertainty_score":0.9997642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02783452546055932,"score_gpt":0.2843952440529242,"score_spread":0.2565607185923648,"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."}}