{"id":"W2138128929","doi":"10.1371/journal.pone.0022885","title":"Fine-Tuning and the Stability of Recurrent Neural Networks","year":2011,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association; Ontario Innovation Trust","keywords":"Computer science; Learning rule; Attractor; Artificial neural network; Integrator; Variety (cybernetics); Context (archaeology); Recurrent neural network; Stability (learning theory); Artificial intelligence; Machine learning; Mathematics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001369549,0.0003524903,0.0004128475,0.0005040274,0.0004041234,0.0007569264,0.0007090265,0.0007511485,0.0009111875],"category_scores_gemma":[0.009477674,0.000311344,0.0003465042,0.000176525,0.001175954,0.001115856,0.0007307729,0.0007598668,0.0002680314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005659226,"about_ca_system_score_gemma":0.0002865261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006527783,"about_ca_topic_score_gemma":0.0007042476,"domain_scores_codex":[0.9994841,0.0001674569,0.00003969376,0.0001355073,0.0001209024,0.00005227697],"domain_scores_gemma":[0.9977223,0.001324226,0.0003377504,0.000286764,0.0002415237,0.00008738114],"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":[0.0001332377,0.00004516253,0.00181479,0.0001003132,0.00008429888,0.0001996322,0.0002199211,0.7609353,0.06594384,0.110007,0.000668712,0.05984771],"study_design_scores_gemma":[0.0000102037,0.00003922851,0.0002833566,0.000006552385,0.00000716404,0.00004613806,0.000008826891,0.9527854,0.004060712,0.04235605,0.0003846505,0.00001162909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1611594,0.0004787069,0.8322013,0.0003176476,0.00004652386,0.00002673524,0.00002428852,0.0006111577,0.005134284],"genre_scores_gemma":[0.9718332,0.0001076784,0.02706708,0.00004492722,0.00001709052,0.0000291469,0.00001627398,0.00005823126,0.0008263846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001369549,"threshold_uncertainty_score":0.007242978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1191296916490951,"score_gpt":0.2287726740829409,"score_spread":0.1096429824338458,"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."}}