{"id":"W2139263136","doi":"10.1109/ijcnn.2006.247153","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":87,"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; Activation function; Artificial intelligence; Multilayer perceptron; Transfer function; Machine learning; Algorithm; Key (lock); Engineering","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":[0.0003122337,0.0002215888,0.0001700704,0.00004759729,0.0003740815,0.0002902224,0.001322211,0.0000599046,0.00004801756],"category_scores_gemma":[0.000009972127,0.0001369071,0.0001223903,0.0004562628,0.000175251,0.0004654498,0.00009994604,0.0003355267,0.00003605144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003827433,"about_ca_system_score_gemma":0.00003367364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001484647,"about_ca_topic_score_gemma":0.00001927378,"domain_scores_codex":[0.998224,0.00002998565,0.000491975,0.0004103223,0.0005139315,0.0003298001],"domain_scores_gemma":[0.9989027,0.0001031672,0.0002358405,0.0002698189,0.0004368785,0.00005164346],"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":[0.00007325195,0.0001928977,0.0008096562,0.00001965055,0.00005867063,0.000001642849,0.0001864102,0.0224107,0.1834334,0.6024836,0.1730941,0.01723598],"study_design_scores_gemma":[0.0004500637,0.0001967687,0.003108433,0.00009791837,0.00003597843,0.00004422337,0.00005738866,0.9514483,0.02791328,0.01061168,0.005628863,0.0004071186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4971744,0.0001690503,0.4393693,0.04662199,0.002923742,0.001479714,0.0000733663,0.0003724934,0.01181598],"genre_scores_gemma":[0.9960992,0.00003484998,0.0002851802,0.0009043532,0.0006143141,0.000104083,0.00001583944,0.00001398674,0.001928137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9290376,"threshold_uncertainty_score":0.558291,"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."}}