{"id":"W3100889249","doi":"10.48550/arxiv.2011.08895","title":"ZORB: A Derivative-Free Backpropagation Algorithm for Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Backpropagation; MNIST database; Artificial neural network; Computer science; Gradient descent; Convolutional neural network; Hyperparameter; Artificial intelligence; Feedforward neural network; Deep learning; Algorithm; Rprop; Time delay neural network; Types of artificial neural networks","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":[0.001514218,0.00218688,0.001473895,0.001342063,0.0007774086,0.001253919,0.003001721,0.002464194,0.005908175],"category_scores_gemma":[0.006028523,0.001031569,0.0009682176,0.001438454,0.0009644047,0.0021532,0.001701182,0.003160314,0.004208258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009417914,"about_ca_system_score_gemma":0.002181208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008484858,"about_ca_topic_score_gemma":0.01435157,"domain_scores_codex":[0.9990971,0.0002172255,0.00007485345,0.0001414798,0.0003854671,0.00008397432],"domain_scores_gemma":[0.9989482,0.0003798004,0.00009837693,0.0001860159,0.0003423771,0.00004528233],"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":[0.0002114895,0.0001311005,0.0008558682,0.0005126781,0.0002794665,0.0002006925,0.0001437626,0.4908391,0.008721343,0.02145659,0.05163973,0.4250083],"study_design_scores_gemma":[0.00005067458,0.00003072022,0.0001362553,0.00003769527,0.0000190938,0.00005920212,0.000009746115,0.9736033,0.003598928,0.01160889,0.01082462,0.00002091575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00347143,0.0008472464,0.9824142,0.0003676822,0.0001699858,0.0001099089,0.0003087563,0.009579233,0.002731663],"genre_scores_gemma":[0.07595447,0.001071146,0.9089924,0.0005564505,0.0001481076,0.0005459886,0.001386266,0.00196734,0.00937794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008484858,"threshold_uncertainty_score":0.01976478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06206015284400915,"score_gpt":0.1953804239124355,"score_spread":0.1333202710684263,"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."}}