{"id":"W2026042300","doi":"10.1016/j.neucom.2005.12.003","title":"Rapid learning and robust recall of long sequences in modular associator networks","year":2006,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Associative property; Modular design; Artificial intelligence; Recall; Sequence (biology); Content-addressable memory; Function (biology); Artificial neural network; Architecture; Recurrent neural network; Machine learning; Mathematics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0002694576,0.0001007511,0.0001624621,0.00005859721,0.0001245035,0.0000810716,0.0002769663,0.00004986639,0.000001108537],"category_scores_gemma":[0.00001518535,0.0001013312,0.00003374454,0.0004540192,0.00003267002,0.0001383313,0.0001966812,0.0002580238,6.987556e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001352467,"about_ca_system_score_gemma":0.00001140064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006718785,"about_ca_topic_score_gemma":0.00001917916,"domain_scores_codex":[0.998907,0.00009828553,0.000282306,0.0003271676,0.0001277858,0.0002574637],"domain_scores_gemma":[0.9994132,0.0002177628,0.0001701875,0.0001310819,0.00003212337,0.00003564897],"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":[9.86304e-7,0.00003038859,0.05973412,0.00001018271,0.000002450354,0.00001963232,0.00004131999,0.8558183,0.0008158016,0.003220193,0.00007098672,0.08023562],"study_design_scores_gemma":[0.0001289358,0.00002737437,0.05924962,0.00003454526,0.000001776232,0.00001048823,0.000004100951,0.9395661,0.0001903162,0.0003603582,0.0003282114,0.00009811657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7007411,0.0004773188,0.2975667,0.0003240627,0.0001140648,0.0001431678,1.559016e-7,0.0001005071,0.0005329304],"genre_scores_gemma":[0.9894412,0.00004190451,0.01025855,0.0000757126,0.0001325424,0.000004155318,0.000001144943,0.000007790056,0.00003704928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2887,"threshold_uncertainty_score":0.4132166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01109549608157187,"score_gpt":0.2161676988960275,"score_spread":0.2050722028144556,"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."}}