{"id":"W2164554122","doi":"10.1109/tnn.2009.2027319","title":"Granular Neural Networks and Their Development Through Context-Based Clustering and Adjustable Dimensionality of Receptive Fields","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Curse of dimensionality; Cluster analysis; Receptive field; Artificial neural network; Artificial intelligence; Context (archaeology); Pattern recognition (psychology)","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":[0.0001548202,0.0003038729,0.0003452901,0.00005623369,0.0004391776,0.00009064583,0.0002956468,0.0001543449,0.000009073114],"category_scores_gemma":[0.000001626916,0.0002537106,0.00009481072,0.0003947023,0.0001203519,0.0003615147,0.0000116584,0.0004780049,3.919204e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002499332,"about_ca_system_score_gemma":0.00001904755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003601416,"about_ca_topic_score_gemma":0.0001449241,"domain_scores_codex":[0.9983552,0.0001055509,0.0004212018,0.000545112,0.0001670679,0.0004058504],"domain_scores_gemma":[0.9989366,0.0003043471,0.0001368511,0.0003984677,0.00007919951,0.0001445187],"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":[0.0000565388,0.00009060781,0.00002182751,0.000007319174,0.0000120138,0.000002913087,0.00017051,0.7861222,0.00008522908,0.0002349232,0.0001165155,0.2130794],"study_design_scores_gemma":[0.0005180611,0.0002316296,0.0007215879,0.00005161122,0.00001425508,0.00001841252,0.00002777323,0.9961193,0.001535626,0.0002647622,0.0002370725,0.000259895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06270111,0.0005630622,0.934515,0.001396854,0.0003233614,0.000355363,0.000004692956,0.0001097247,0.00003080892],"genre_scores_gemma":[0.9938734,0.0001314017,0.003479662,0.002371942,0.00005896463,0.00003402065,0.00000431165,0.00001309257,0.00003320105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9311723,"threshold_uncertainty_score":0.9999915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02072436511733904,"score_gpt":0.2366613044974035,"score_spread":0.2159369393800644,"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."}}