{"id":"W2072499402","doi":"10.1109/tnn.2005.860855","title":"A Sequential Dynamic Heteroassociative Memory for Multistep Pattern Recognition and One-to-Many Association","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Backpropagation; Artificial intelligence; Bidirectional associative memory; Pattern recognition (psychology); Associative property; Content-addressable memory; Sequence learning; Artificial neural network; Feed forward; Association (psychology); Context (archaeology); Set (abstract data type); Task (project management); Content-addressable storage; Feedforward neural network; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001758058,0.0002194696,0.0002304394,0.0001056229,0.000449915,0.0002205494,0.0002439493,0.0001594972,0.000007198264],"category_scores_gemma":[0.000002933436,0.0002368756,0.0001456992,0.0003497999,0.00002256141,0.0003467758,0.000005975185,0.0002992581,0.00001442551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002207136,"about_ca_system_score_gemma":0.00001255641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001557842,"about_ca_topic_score_gemma":0.0007206329,"domain_scores_codex":[0.9983441,0.00009352524,0.0003427796,0.0005522681,0.000229007,0.0004383732],"domain_scores_gemma":[0.9989569,0.0003613311,0.0001935104,0.0002518694,0.0001244731,0.0001119784],"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":[0.00006167424,0.0003436354,0.00004163594,0.00001529492,0.00008893045,0.000003690119,0.0001721187,0.3399441,0.00159152,0.00006869579,0.001194028,0.6564746],"study_design_scores_gemma":[0.0008834649,0.0001738615,0.0008529269,0.00002820836,0.00004875275,0.000005225294,0.000007785093,0.9957854,0.0009283284,0.0009021743,0.00008598992,0.0002979201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06040879,0.00002419476,0.9358739,0.001750529,0.0007373775,0.0008659947,0.00008228508,0.0002147824,0.00004217166],"genre_scores_gemma":[0.9939383,0.00002607453,0.003959952,0.0009386407,0.0002277175,0.0004476751,0.00003330882,0.00002555894,0.0004027661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335295,"threshold_uncertainty_score":0.9659507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0214230759761563,"score_gpt":0.2461983975679023,"score_spread":0.224775321591746,"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."}}