{"id":"W2996170846","doi":"","title":"Training Recurrent Neural Networks Online by Learning Explicit State Variables","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Recurrent neural network; Computer science; Truncation (statistics); Computation; Focus (optics); Machine learning; Artificial intelligence; Variety (cybernetics); Artificial neural network; Online learning; Algorithm; Mathematical optimization; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002799223,0.000263012,0.0002436786,0.0001644506,0.0004136965,0.0008583762,0.001004356,0.00007187914,0.0005468108],"category_scores_gemma":[0.0008406938,0.0002841891,0.0001125234,0.0004296384,0.00005618511,0.0008795665,0.000247353,0.001209578,0.0001128612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006363125,"about_ca_system_score_gemma":0.00009243545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004106988,"about_ca_topic_score_gemma":0.0000049931,"domain_scores_codex":[0.9972682,0.0003786664,0.0005091439,0.0007608499,0.0006800468,0.0004030995],"domain_scores_gemma":[0.9983689,0.0004351256,0.0003599082,0.0002239048,0.0003262157,0.0002859958],"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":[0.00006201787,0.0001206033,0.002189265,0.000006567843,0.0001011227,0.00003086738,0.01435271,0.6738248,0.002225689,0.04327198,0.001205074,0.2626093],"study_design_scores_gemma":[0.0005396219,0.0002006177,0.0009876038,0.00004967855,0.000006627648,0.000008416614,0.002495111,0.978106,0.00004122633,0.0003971029,0.01688333,0.0002847194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02519315,0.00007166671,0.9416239,0.0150996,0.000754414,0.0002291313,0.00001473598,0.0007414087,0.016272],"genre_scores_gemma":[0.9910021,0.0001515823,0.00502457,0.001305308,0.00021991,0.00003780469,0.0003212127,0.00002940237,0.001908146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9658089,"threshold_uncertainty_score":0.999961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1140512496037991,"score_gpt":0.3407093050386591,"score_spread":0.22665805543486,"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."}}