{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009334743,0.001232085,0.0009649581,0.0003336345,0.000331362,0.0007889798,0.001722335,0.00189406,0.006766171],"category_scores_gemma":[0.003396123,0.001068542,0.0007408597,0.0004627231,0.0006082864,0.001851403,0.001351698,0.002587694,0.001605364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006716084,"about_ca_system_score_gemma":0.0007565154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004891611,"about_ca_topic_score_gemma":0.01171713,"domain_scores_codex":[0.9997415,0.00006026553,0.00001866136,0.00007578624,0.00006372469,0.00003996771],"domain_scores_gemma":[0.9990972,0.0005594951,0.00004713391,0.0001172125,0.000135337,0.00004360829],"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":[0.0001635621,0.0001072929,0.000440514,0.0001346812,0.0001098295,0.00008951702,0.0000711543,0.7320424,0.00604606,0.01628892,0.007404136,0.237102],"study_design_scores_gemma":[0.000006398788,0.00001384097,0.00002878816,0.000004489872,0.000005218058,0.000005898776,0.000002898459,0.9960939,0.0005217167,0.003032288,0.0002818748,0.000002608724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03393659,0.00101952,0.9553301,0.0004160288,0.0002522645,0.00005098038,0.0001691393,0.002316938,0.006508525],"genre_scores_gemma":[0.4433499,0.0005464263,0.5321154,0.0003933047,0.0001801778,0.0002372796,0.0009945125,0.0009159314,0.02126716],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006766171,"threshold_uncertainty_score":0.0226351,"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."}}