{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003604915,0.001306642,0.0009823715,0.0007559572,0.0004473464,0.00102968,0.001167747,0.001260445,0.001650606],"category_scores_gemma":[0.01720908,0.0008422976,0.0006240071,0.0007398401,0.002258505,0.003389735,0.002434552,0.002547208,0.0003164541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009126064,"about_ca_system_score_gemma":0.0009300134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004057998,"about_ca_topic_score_gemma":0.004765189,"domain_scores_codex":[0.9990057,0.0004778117,0.00005549358,0.0001757991,0.0001938729,0.00009131946],"domain_scores_gemma":[0.9914927,0.006552231,0.0007149344,0.0004439632,0.0006091151,0.0001870776],"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":[0.0001049183,0.00005652142,0.001027876,0.0001179247,0.00006847199,0.0001241555,0.0001419782,0.8271533,0.004826208,0.1330934,0.001079272,0.03220592],"study_design_scores_gemma":[0.000004850192,0.00002496609,0.00008593875,0.00001004292,0.000004605964,0.00001455604,0.000006070834,0.9676317,0.0004937997,0.0314903,0.0002264835,0.000006678708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02693325,0.0008222528,0.9696591,0.0006507508,0.00004402371,0.00002432649,0.00004763449,0.0001903199,0.001628326],"genre_scores_gemma":[0.7268248,0.00327364,0.261302,0.0005583695,0.0003118211,0.0002577785,0.0004177403,0.0003175227,0.006736356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004057998,"threshold_uncertainty_score":0.01906484,"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."}}