{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000174585,0.00005492768,0.0001097077,0.00001348584,0.00006678974,0.000009971621,0.00008894598,0.0000188738,0.00004086876],"category_scores_gemma":[0.0002996634,0.00003473665,0.00002358473,0.00009140697,0.0001773448,0.00006005267,0.0000663238,0.0001222654,9.597364e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004619076,"about_ca_system_score_gemma":0.000003053142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001681547,"about_ca_topic_score_gemma":0.00001246645,"domain_scores_codex":[0.9993885,0.0001087404,0.0001246913,0.0001524291,0.0001226874,0.0001029798],"domain_scores_gemma":[0.9995091,0.0002185188,0.00006674515,0.0001569159,0.00002219249,0.00002654908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001938411,0.002907267,0.06619411,0.000274245,0.00006108636,0.000009827861,0.002885621,0.00008046498,0.8634276,0.03082913,0.0000714425,0.03132077],"study_design_scores_gemma":[0.0009861493,0.0003128655,0.01900018,0.00005664027,0.00006578685,0.000003402681,0.00003338363,0.8265789,0.1506497,0.00215701,0.000008440874,0.0001475705],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984987,0.0000375398,0.0001029612,0.0002268889,0.00008663139,0.0001689334,0.000003029821,0.00001866044,0.0008566912],"genre_scores_gemma":[0.9997271,0.00003427984,0.00005425822,0.0001187023,0.00002735251,0.000007088466,5.226569e-7,0.000004661461,0.0000260069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8264984,"threshold_uncertainty_score":0.1416519,"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."}}