{"id":"W4248290806","doi":"10.1109/ijcnn.2006.1716763","title":"Improving the Convergence of Backpropagation by Opposite Transfer Functions","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Backpropagation; Computer science; Convergence (economics); Benchmark (surveying); Perceptron; Artificial neural network; Rate of convergence; Artificial intelligence; Activation function; Multilayer perceptron; Machine learning; Algorithm; Key (lock)","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":[0.003283952,0.001254416,0.0009308086,0.0009587515,0.0004441797,0.001089929,0.001344784,0.00197985,0.002001127],"category_scores_gemma":[0.01368438,0.0004063949,0.0006816783,0.0006333059,0.0009203802,0.001793134,0.001392003,0.001889289,0.0009617704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004941819,"about_ca_system_score_gemma":0.0008076918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001160529,"about_ca_topic_score_gemma":0.0008195646,"domain_scores_codex":[0.9988112,0.0003186696,0.00008851811,0.0001256518,0.0005471084,0.0001088123],"domain_scores_gemma":[0.996044,0.002038846,0.000269058,0.0004070563,0.001134857,0.00010611],"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":[0.0004742719,0.0002809324,0.001454493,0.0002796949,0.0001334783,0.0002578203,0.000133401,0.7106795,0.02838933,0.02109156,0.002671099,0.2341545],"study_design_scores_gemma":[0.00002993591,0.00008775524,0.0001641589,0.00001077729,0.00001424046,0.00007433945,0.000008604177,0.9863239,0.008053888,0.004155588,0.00106525,0.00001145192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05065626,0.0003181325,0.9422725,0.0002464695,0.0002064513,0.00005981188,0.00001904482,0.0009543624,0.005267011],"genre_scores_gemma":[0.5445768,0.0003787166,0.4503033,0.0002320449,0.00008901852,0.0001698379,0.0001139295,0.0003285922,0.003807776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003283952,"threshold_uncertainty_score":0.01736736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02468220524140385,"score_gpt":0.2277334466673562,"score_spread":0.2030512414259524,"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."}}