{"id":"W2106485397","doi":"10.1109/tnn.2005.852861","title":"NDRAM: Nonlinear Dynamic Recurrent Associative Memory for Learning Bipolar and Nonbipolar Correlated Patterns","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Hebbian theory; Bidirectional associative memory; Content-addressable memory; Attractor; Computer science; Artificial neural network; Content-addressable storage; Hopfield network; Learning rule; Nonlinear system; Spurious relationship; Leabra; Artificial intelligence; Recurrent neural network; Competitive learning; Machine learning; Mathematics; Wake-sleep algorithm","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":[0.0001811646,0.0002912304,0.000271365,0.0001103136,0.0006913856,0.0001735524,0.0004024589,0.0001771383,0.00001150321],"category_scores_gemma":[0.000004925251,0.0002820571,0.0001717239,0.0004246161,0.00005186371,0.0004315708,0.000009089458,0.0009037431,0.00001125357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001097316,"about_ca_system_score_gemma":0.00001829366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002086304,"about_ca_topic_score_gemma":0.0001615215,"domain_scores_codex":[0.9982024,0.0001174439,0.0003593448,0.0006060039,0.000201874,0.0005128834],"domain_scores_gemma":[0.9987855,0.00042805,0.0001736847,0.0003327185,0.0000952516,0.0001847838],"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":[0.00002451059,0.0001221775,0.00004150879,0.000006138731,0.00003802015,0.000001762595,0.0001640996,0.4435263,0.0001009191,0.00004111768,0.000100941,0.5558325],"study_design_scores_gemma":[0.0005637292,0.0002827138,0.0003088932,0.00003508458,0.00004141665,0.00001697429,0.00001956896,0.9947966,0.0002718255,0.00002734097,0.003334137,0.0003017376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04264355,0.0005910819,0.9533556,0.001649832,0.0007806538,0.0006135147,0.00003652702,0.0003136974,0.00001556575],"genre_scores_gemma":[0.9920353,0.0006822976,0.005964261,0.0005386549,0.0002105858,0.0001455334,0.00001870079,0.00003769925,0.0003669361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9493918,"threshold_uncertainty_score":0.9999632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01019018009339822,"score_gpt":0.2467939434584401,"score_spread":0.2366037633650418,"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."}}