{"id":"W3104722529","doi":"","title":"Untangling tradeoffs between recurrence and self-attention in artificial neural networks","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence","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":[0.003737351,0.0003594987,0.0008378269,0.0005994836,0.0006885982,0.001554243,0.001537572,0.001873879,0.003208256],"category_scores_gemma":[0.04480108,0.0005136036,0.0003590957,0.0004528467,0.001276968,0.005285366,0.001596849,0.001818032,0.0003174858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008628885,"about_ca_system_score_gemma":0.0005806114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001345581,"about_ca_topic_score_gemma":0.002348921,"domain_scores_codex":[0.9990338,0.0004983259,0.00006185035,0.0001746636,0.0001269074,0.0001044557],"domain_scores_gemma":[0.9673262,0.02806149,0.001568433,0.001671684,0.0008423126,0.0005300072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001022167,0.0003578103,0.01435829,0.0005386501,0.0002060639,0.0003903206,0.001643183,0.3473712,0.01261411,0.403758,0.004890818,0.2128495],"study_design_scores_gemma":[0.00003629737,0.0001168814,0.001877403,0.00002704039,0.00003565331,0.00007603449,0.00008951263,0.8066214,0.00146521,0.1892188,0.0004122555,0.00002358082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6708954,0.003500662,0.3083331,0.005155469,0.0002056088,0.00004730536,0.0001212002,0.0005443287,0.01119692],"genre_scores_gemma":[0.9908296,0.0002223273,0.007186425,0.0001173586,0.00007280114,0.00002480532,0.00002488237,0.00005405418,0.001467718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003737351,"threshold_uncertainty_score":0.0197652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0300689481696927,"score_gpt":0.2506744529650285,"score_spread":0.2206055047953358,"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."}}