{"id":"W4405055819","doi":"10.1109/tetci.2024.3502463","title":"Convex-Concave Programming: An Effective Alternative for Optimizing Shallow Neural Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Burnaby Hospital; Université du Québec à Montréal","funders":"","keywords":"Regular polygon; Concave function; Artificial neural network; Computer science; Mathematical optimization; Mathematics; Artificial intelligence; Geometry","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":[0.0001728576,0.0001777073,0.0001502418,0.0002504998,0.0001163383,0.0001268045,0.0001296219,0.00007609736,0.00003323632],"category_scores_gemma":[0.000006971255,0.0001998472,0.00009263845,0.0003094109,0.0000381324,0.000263529,0.000001191585,0.0004420498,0.000006906715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001470689,"about_ca_system_score_gemma":0.00001301456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001345343,"about_ca_topic_score_gemma":0.00003606418,"domain_scores_codex":[0.9989813,0.00004641947,0.0002934004,0.0002924701,0.0001532598,0.0002331235],"domain_scores_gemma":[0.9992975,0.0004610472,0.00002242387,0.00008877837,0.00006979031,0.00006043389],"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":[0.0000102124,0.00002216008,0.000006672769,0.00004125347,0.00003646258,0.000006227083,0.0009617939,0.7593293,0.000006485231,0.00216079,0.000003326395,0.2374154],"study_design_scores_gemma":[0.00008824188,0.00009690489,0.00007187151,0.00009773129,0.0000130414,0.000005568935,0.0001604503,0.9969125,0.0003841649,0.001720138,0.0002484742,0.0002008869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004972996,0.000146604,0.9917991,0.0001350761,0.002010532,0.0004535911,0.000003059364,0.0003623627,0.0001166516],"genre_scores_gemma":[0.9785951,0.00001861346,0.02086159,0.00005662132,0.0001835263,0.0001773087,0.00001523214,0.00003907732,0.00005293763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9736221,"threshold_uncertainty_score":0.8149534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03910884977110845,"score_gpt":0.3216815543840167,"score_spread":0.2825727046129082,"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."}}