{"id":"W2100283156","doi":"10.1109/icnn.1996.549082","title":"Modular neural network architectures for classification","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Modular design; Computer science; Artificial neural network; Divide and conquer algorithms; Modular neural network; Artificial intelligence; Classifier (UML); Machine learning; Task (project management); Time delay neural network; Decomposition; Engineering; Algorithm","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":[0.00024362,0.0003903919,0.0003680578,0.0001735288,0.000278447,0.0004183511,0.002078001,0.0001580896,0.00007870701],"category_scores_gemma":[0.00006593468,0.0003558322,0.0002429472,0.0005405002,0.0001412025,0.000375693,0.0002591313,0.0004657799,0.00001079429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005438198,"about_ca_system_score_gemma":0.00001252974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006258172,"about_ca_topic_score_gemma":0.000003318355,"domain_scores_codex":[0.9972473,0.00001818997,0.0006784567,0.0008654175,0.0005728706,0.0006177609],"domain_scores_gemma":[0.9979189,0.0001986422,0.0005659439,0.0003156842,0.0008095478,0.0001912985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001287747,0.0002690242,0.002337248,0.00003905601,0.00009243777,0.000002463965,0.0001732012,0.1380905,0.004973035,0.7476169,0.01933582,0.08694152],"study_design_scores_gemma":[0.0004389496,0.0002524016,0.002236116,0.00007134536,0.00001466725,0.00002115618,0.00001978614,0.9811339,0.0003946929,0.01260614,0.002470573,0.0003403119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7153641,0.000893429,0.1790348,0.06155861,0.004651715,0.003783354,0.00007824543,0.001290337,0.03334534],"genre_scores_gemma":[0.9904781,0.0001390991,0.006178489,0.001164186,0.00123407,0.0002716325,0.00002059604,0.00003407156,0.0004797752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8430434,"threshold_uncertainty_score":0.9998894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05898314501375335,"score_gpt":0.2745676832261193,"score_spread":0.215584538212366,"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."}}