{"id":"W71081281","doi":"10.1007/978-3-642-35289-8_27","title":"Training Deep and Recurrent Networks with Hessian-Free Optimization","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":206,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Implementation; Hessian matrix; Heuristic; Artificial intelligence; Training (meteorology); Artificial neural network; Machine learning; Deep neural networks; Computer engineering; Software 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003635343,0.0003696699,0.0003239901,0.0002416423,0.0003039303,0.0004593157,0.001757611,0.0001847949,0.00001007071],"category_scores_gemma":[0.00001241834,0.0002937987,0.00004182478,0.000479069,0.000435866,0.000589328,0.000839366,0.0005835178,0.000002431513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007890022,"about_ca_system_score_gemma":0.0001161703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003396269,"about_ca_topic_score_gemma":0.00005172738,"domain_scores_codex":[0.9977104,0.00001851376,0.0002926868,0.0009605451,0.0004546347,0.0005632065],"domain_scores_gemma":[0.9982204,0.0002174319,0.0002214886,0.001032307,0.0001005162,0.0002078703],"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":[0.000001702828,0.000006239874,0.000009047887,0.000004811924,0.000002742438,0.000004361664,0.00020407,0.4036286,7.72042e-7,0.009189485,0.000005922901,0.5869423],"study_design_scores_gemma":[0.0001603191,0.00009481824,0.00005387989,0.000206516,0.00000826779,0.00007700894,1.222942e-7,0.983337,0.000008651347,0.01484613,0.0008168868,0.0003903844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000008862313,0.00188261,0.995007,0.0007436782,0.0005374523,0.0003177579,0.000001271876,0.0001121557,0.0013892],"genre_scores_gemma":[0.06546018,0.0003130942,0.9324282,0.0009029586,0.0007587145,0.00002295564,0.000007569538,0.00003426948,0.00007199664],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5865519,"threshold_uncertainty_score":0.9999514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02176382442885493,"score_gpt":0.2338243518035695,"score_spread":0.2120605273747145,"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."}}