{"id":"W2344244807","doi":"10.1109/tcyb.2015.2492468","title":"Extreme Learning Machine With Subnetwork Hidden Nodes for Regression and Classification","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extreme learning machine; Subnetwork; Bottleneck; Computer science; Artificial intelligence; Generalization; Artificial neural network; Backpropagation; Machine learning; Support vector machine; Residual; Feedforward neural network; Feed forward; Pattern recognition (psychology); Algorithm; Engineering; Mathematics; Computer network","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":[0.0002616996,0.000149599,0.0001322727,0.00008856218,0.0002262396,0.0001160589,0.0002065818,0.00007450728,0.000004046077],"category_scores_gemma":[0.00001199849,0.0001160761,0.00003239734,0.0002033118,0.00004675865,0.0001442701,0.000002689356,0.0002329447,0.00001409928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003396493,"about_ca_system_score_gemma":0.00004035792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003916712,"about_ca_topic_score_gemma":0.00004746252,"domain_scores_codex":[0.9990154,0.00008477688,0.0001473911,0.0003238946,0.0002241238,0.0002044169],"domain_scores_gemma":[0.9992552,0.0001428372,0.00008275278,0.0002789908,0.0000965725,0.0001435813],"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":[0.0002403061,0.0002397363,0.002412144,0.00004040284,0.00004977507,0.00000581989,0.002630627,0.08669832,0.000390405,0.003244146,0.0008590601,0.9031892],"study_design_scores_gemma":[0.001106988,0.000608762,0.001704923,0.00007626026,0.00003134101,0.00002983639,0.00006946367,0.9836458,0.0007014918,0.0006238107,0.01115386,0.0002474406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0191422,0.0001372802,0.9782784,0.0009474171,0.0002232436,0.0001541841,0.000001896603,0.0002037725,0.0009115957],"genre_scores_gemma":[0.9403904,0.00004995407,0.05665236,0.00006572373,0.00005065673,0.00002874552,0.000003662227,0.00001959599,0.002738876],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.921626,"threshold_uncertainty_score":0.4733444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05160575226254047,"score_gpt":0.2679118930501463,"score_spread":0.2163061407876058,"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."}}