{"id":"W4285606915","doi":"10.24963/ijcai.2022/246","title":"A Solver + Gradient Descent Training Algorithm for Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Maxima and minima; MNIST database; Solver; Computer science; Artificial neural network; Gradient descent; Algorithm; Convergence (economics); Stochastic gradient descent; Artificial intelligence; Mathematical optimization; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008229034,0.001806368,0.0008471891,0.0006440952,0.0003898569,0.0007987634,0.001579477,0.001294647,0.006802053],"category_scores_gemma":[0.002413429,0.000808666,0.0006699919,0.0006847887,0.0006318809,0.00090351,0.001381183,0.002013635,0.002796654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000806982,"about_ca_system_score_gemma":0.001680221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004630017,"about_ca_topic_score_gemma":0.008323879,"domain_scores_codex":[0.999598,0.0001034688,0.00002686263,0.00008695778,0.0001380074,0.00004683269],"domain_scores_gemma":[0.9995494,0.0002173583,0.00003703634,0.00006182901,0.0001070388,0.00002729308],"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":[0.0001106191,0.0001106018,0.0007953348,0.0001887011,0.0001019568,0.0001205392,0.00007034596,0.6449279,0.00525123,0.02917836,0.01581476,0.3033296],"study_design_scores_gemma":[0.00002523375,0.00001930282,0.00003221913,0.00001033153,0.000004580836,0.00002296834,0.000004728412,0.9895415,0.00112675,0.005691999,0.003515867,0.00000438088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002043938,0.0001260604,0.9927146,0.0001100875,0.00004652191,0.00005444328,0.00009621488,0.002797423,0.002010742],"genre_scores_gemma":[0.04432267,0.00009912399,0.9502601,0.0002251054,0.00003152178,0.0002829015,0.0004157791,0.0006571373,0.003705639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006802053,"threshold_uncertainty_score":0.02275515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07515808732222891,"score_gpt":0.2862519700429457,"score_spread":0.2110938827207168,"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."}}