{"id":"W2963421552","doi":"","title":"Architectural Complexity Measures of Recurrent Neural Networks","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Université de Montréal","funders":"","keywords":"Recurrent neural network; Feed forward; Computer science; Computability; Feedforward neural network; Graph; Nonlinear system; Computational complexity theory; Measure (data warehouse); Dependency (UML); Artificial intelligence; Algorithm; Theoretical computer science; Artificial neural network; Data mining; Engineering; Control 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":[0.001237546,0.0009218441,0.0006242998,0.001412418,0.0005165644,0.0013952,0.00114325,0.000968564,0.002322866],"category_scores_gemma":[0.01005294,0.0005046182,0.0006777608,0.0006269577,0.001554807,0.004207855,0.001325676,0.001405119,0.0002586732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001318288,"about_ca_system_score_gemma":0.0005743502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008367004,"about_ca_topic_score_gemma":0.001032048,"domain_scores_codex":[0.999353,0.0001682348,0.00005298672,0.0001380036,0.0002021598,0.00008553528],"domain_scores_gemma":[0.9935427,0.004064581,0.0009296366,0.0004042398,0.00074351,0.0003152525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008454468,0.00005516106,0.004425659,0.0002626808,0.0000934639,0.0002413643,0.0002966633,0.5391436,0.0107503,0.4142326,0.001040073,0.02937403],"study_design_scores_gemma":[0.000006397086,0.00004854036,0.001183783,0.00001599643,0.00002161647,0.00008108193,0.00004207349,0.7997072,0.001753816,0.1965159,0.0006036469,0.00001997135],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2618208,0.0009515123,0.7287325,0.0005741098,0.00004419361,0.00007153561,0.000190893,0.000292656,0.00732174],"genre_scores_gemma":[0.9446356,0.0006187781,0.05217802,0.0000812716,0.00007355944,0.0001310781,0.0002537541,0.0001003881,0.001927493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002322866,"threshold_uncertainty_score":0.009564936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05000399624100138,"score_gpt":0.2526875896740306,"score_spread":0.2026835934330292,"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."}}