{"id":"W2904474124","doi":"10.1016/j.procs.2018.11.102","title":"Generating Cognitive Context with Feature-Extracting Bidirectional Associative Memory","year":2018,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Content-addressable memory; Associative property; Feature (linguistics); Context (archaeology); Limiting; Recall; Cognition; Pattern recognition (psychology); Artificial intelligence; Bidirectional associative memory; Machine learning; Artificial neural network; Cognitive psychology","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":[0.0005040122,0.0001714863,0.0001458309,0.0001141597,0.001168846,0.0005859433,0.0009018371,0.0000389618,0.00000548641],"category_scores_gemma":[0.0000719345,0.0001372382,0.00003293999,0.001666063,0.0005252184,0.001305462,0.0003559652,0.0002272315,0.00004893606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007315962,"about_ca_system_score_gemma":0.000350391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001262102,"about_ca_topic_score_gemma":0.00003048573,"domain_scores_codex":[0.997988,0.00003242445,0.0001599422,0.0007867267,0.0005705394,0.0004623198],"domain_scores_gemma":[0.9982247,0.0002679111,0.0002032708,0.0002394515,0.0009026644,0.000161991],"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":[0.00001525478,0.000154189,0.003494976,0.00001070323,0.00003755638,0.00001416692,0.005312039,0.0003622235,0.005931819,0.01245091,0.003267302,0.9689488],"study_design_scores_gemma":[0.0003537109,0.0002896661,0.007372983,0.00008214399,0.000007797449,0.0001119545,0.00007706536,0.9715754,0.01877879,0.0004729802,0.0005050434,0.0003724102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1123045,0.00004793663,0.8838078,0.001200188,0.0005860907,0.0002628068,0.000002092344,0.0002489212,0.001539736],"genre_scores_gemma":[0.7962582,0.000001954633,0.2010087,0.001542427,0.001006193,0.00003987312,0.000001063705,0.000007467557,0.0001341356],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9712132,"threshold_uncertainty_score":0.8989938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01576960875963367,"score_gpt":0.261036625269699,"score_spread":0.2452670165100653,"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."}}