{"id":"W2964304579","doi":"","title":"On orthogonality and learning recurrent networks with long term dependencies","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Orthogonality; Backpropagation; Artificial neural network; Computer science; Convergence (economics); Term (time); Stability (learning theory); Property (philosophy); Matrix (chemical analysis); Norm (philosophy); Applied mathematics; Mathematical optimization; Gradient method; Mathematics; Algorithm; Artificial intelligence; Machine learning","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":[0.0001649899,0.0001859829,0.0001489699,0.00007822597,0.0003712286,0.0003521306,0.0002736021,0.00006020164,0.0001036719],"category_scores_gemma":[0.0001329871,0.000159396,0.00003069193,0.00001882398,0.0000704089,0.000145966,0.00008647233,0.0009521249,0.000009312996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003591231,"about_ca_system_score_gemma":0.000009890719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005597006,"about_ca_topic_score_gemma":0.0001118499,"domain_scores_codex":[0.9991512,0.00005795662,0.0001318724,0.0002358092,0.0002513874,0.0001717221],"domain_scores_gemma":[0.9994639,0.00008660552,0.0001097789,0.0001927479,0.00009027609,0.000056661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003768749,0.00006179783,0.4424607,0.00002651339,0.0002628612,0.0001855605,0.0003233241,0.2527148,0.001167858,0.03403238,0.00009076093,0.2682965],"study_design_scores_gemma":[0.0003802687,0.0003003916,0.2348757,0.0005608885,0.00001412687,0.00003250476,0.00002406827,0.761909,0.0004861047,0.0005748292,0.0005209588,0.000321134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9385608,0.0001168224,0.02188507,0.0002561799,0.0002957488,0.0000981503,0.000002765625,0.0004666147,0.03831783],"genre_scores_gemma":[0.998873,0.0002106262,0.0003425752,0.0000396252,0.00009821677,0.000007794613,0.00002407454,0.00002529,0.0003787889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5091943,"threshold_uncertainty_score":0.6499982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0326125001541815,"score_gpt":0.2885483512715729,"score_spread":0.2559358511173914,"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."}}