{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002976621,0.001604806,0.001193251,0.001401664,0.0005334187,0.001003371,0.001628535,0.001578837,0.002083217],"category_scores_gemma":[0.01355286,0.0005910216,0.0005701203,0.00137329,0.0007071438,0.002405645,0.0009923351,0.001995662,0.001404082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006096113,"about_ca_system_score_gemma":0.001095817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003897948,"about_ca_topic_score_gemma":0.004504863,"domain_scores_codex":[0.9990773,0.0002983055,0.00006112189,0.0001161579,0.0003973575,0.00004977773],"domain_scores_gemma":[0.9960474,0.002066783,0.0002575228,0.0004151383,0.001131591,0.00008151362],"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":[0.0001539996,0.0002190566,0.001299573,0.0002584233,0.0001486906,0.00007844242,0.00009257085,0.5964992,0.0056912,0.01223373,0.005745198,0.3775799],"study_design_scores_gemma":[0.00002127432,0.00003356891,0.0001968943,0.00001029544,0.000009150591,0.0000214722,0.000005320249,0.9924339,0.001762248,0.004552988,0.0009440721,0.000008748592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0107801,0.0009941778,0.9851423,0.0001791882,0.0001166056,0.00005856221,0.0000328044,0.001513875,0.001182401],"genre_scores_gemma":[0.1150754,0.000619821,0.8804961,0.000171073,0.0001194307,0.0001530923,0.0001908217,0.0004800924,0.00269419],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003897948,"threshold_uncertainty_score":0.01574206,"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."}}