{"id":"W2169923338","doi":"10.1109/ijcnn.2009.5178798","title":"Improving gradient-based learning algorithms for large scale feedforward networks","year":2009,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmark (surveying); Computer science; Backpropagation; Convergence (economics); Artificial neural network; Scale (ratio); Feed forward; Algorithm; Feedforward neural network; Artificial intelligence; Machine learning; Rate of convergence; Simple (philosophy); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002068742,0.0001173287,0.0001202011,0.00004101014,0.0003726811,0.0001839179,0.0004600981,0.00005133871,0.000006425475],"category_scores_gemma":[0.000007495095,0.0001011688,0.0001011148,0.0003182731,0.00000911085,0.0002067243,0.0000538432,0.0001421475,0.000008365941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001903879,"about_ca_system_score_gemma":0.00001809318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006752332,"about_ca_topic_score_gemma":0.000007321286,"domain_scores_codex":[0.9989021,0.00001529785,0.0001678086,0.000360383,0.0001087361,0.0004456421],"domain_scores_gemma":[0.9993941,0.00006795173,0.00007065093,0.000299685,0.00005709912,0.0001105683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007106968,0.0001618812,0.0002805497,0.00000686035,0.000006182742,0.000001874335,0.00006795834,0.06366747,0.0005569131,0.08541737,0.005335338,0.8444905],"study_design_scores_gemma":[0.0003505537,0.0001280823,0.0004069858,0.000005460393,0.000003976416,0.000001577036,0.000007873063,0.9829954,0.0004792157,0.0008164613,0.01466058,0.0001438264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001448334,0.00005528776,0.9954299,0.00184251,0.0001296386,0.0002879761,0.000001011383,0.0003401294,0.000465159],"genre_scores_gemma":[0.7227526,0.000004562868,0.2742187,0.001874607,0.0002472447,0.0000551062,0.00001268959,0.000009304563,0.0008251136],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9193279,"threshold_uncertainty_score":0.4125545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244187843591799,"score_gpt":0.2487592542064199,"score_spread":0.2363173757705019,"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."}}