{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002045261,0.0001542411,0.0001949296,0.00008738098,0.0002205873,0.0009034373,0.0003418039,0.00008166053,4.405306e-7],"category_scores_gemma":[0.00001690303,0.0001446779,0.00002948371,0.000823935,0.00002418313,0.003443874,0.00008607648,0.0002732518,0.000006858542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002814322,"about_ca_system_score_gemma":0.00002284129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001437748,"about_ca_topic_score_gemma":0.000001723866,"domain_scores_codex":[0.9985648,0.000060271,0.0006390207,0.0002372263,0.0002286527,0.0002700704],"domain_scores_gemma":[0.9993161,0.00004913673,0.0002937572,0.0001350584,0.0000758351,0.0001300898],"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":[0.00001767052,0.00005140745,0.02117843,0.0006342312,0.0000123036,0.000006704969,0.005571794,0.1571118,0.0001625381,0.01006162,0.0005164473,0.804675],"study_design_scores_gemma":[0.0001481297,0.00004013193,0.00387705,0.00005642483,0.000004779919,0.00001232425,0.0001244329,0.9948792,0.00002047705,0.00005991037,0.0006200691,0.0001570472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4281429,0.0005432384,0.5632858,0.005769031,0.0005298267,0.0008288231,0.000005851631,0.000679974,0.0002145658],"genre_scores_gemma":[0.9985639,0.00001152893,0.0006045639,0.0004558935,0.0002963145,0.00003977157,0.00002033148,0.000005877978,0.00000178102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8377674,"threshold_uncertainty_score":0.8711866,"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."}}