{"id":"W1515673448","doi":"10.1109/ijcnn.2005.1556113","title":"Training the SOFM efficiently: an example from intrusion detection","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Artificial intelligence; Intrusion detection system; Construct (python library); Machine learning; Feature (linguistics); Set (abstract data type); Reduction (mathematics); Unsupervised learning; Feature selection; Training (meteorology); Training set; Pattern recognition (psychology); Data mining; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000671949,0.000415572,0.0003085001,0.0002455893,0.0006184326,0.001150303,0.001391853,0.0002180416,0.0002541907],"category_scores_gemma":[0.00002874306,0.0003338809,0.0001585235,0.0003772317,0.000134733,0.001444637,0.0002116451,0.0008085718,0.00005450803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002094134,"about_ca_system_score_gemma":0.00004997676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00100454,"about_ca_topic_score_gemma":0.0009738604,"domain_scores_codex":[0.9965908,0.00007424726,0.0006904845,0.0009931315,0.0009015966,0.0007497544],"domain_scores_gemma":[0.9985512,0.0001076189,0.0004606879,0.000338789,0.000373103,0.0001685998],"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":[0.0006330006,0.0008487094,0.0001493973,0.00001347891,0.0001363041,0.00003538638,0.003071799,0.1683374,0.04478466,0.1122689,0.02279652,0.6469245],"study_design_scores_gemma":[0.0005215019,0.0001799615,0.0007559077,0.00007356967,0.00001280437,0.00004731742,0.0001410319,0.975154,0.00505576,0.005360536,0.01230133,0.0003962788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5508909,0.0001379178,0.4260028,0.004207175,0.009060815,0.0007557915,0.00001157125,0.0009378228,0.007995195],"genre_scores_gemma":[0.9934569,0.0001067275,0.001099226,0.001164578,0.003728675,0.00006260234,0.00003716466,0.00002996279,0.0003141579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8068166,"threshold_uncertainty_score":0.9999113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06732392603221184,"score_gpt":0.2592901926970337,"score_spread":0.1919662666648219,"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."}}