{"id":"W2472390602","doi":"10.1109/tcyb.2015.2481713","title":"Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Subnetwork; Extreme learning machine; Computer science; Feature learning; Artificial intelligence; Unsupervised learning; Machine learning; Cluster analysis; Semi-supervised learning; Sparse approximation; Pattern recognition (psychology); Representation (politics); Feature (linguistics); Supervised learning; Artificial neural network; Competitive learning; Generalization; Mathematics","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":[0.0003844162,0.0002147878,0.0001981885,0.0001386078,0.0003500418,0.0001707683,0.0003301169,0.00009017878,0.00001459402],"category_scores_gemma":[0.00003860855,0.0001908892,0.00008597135,0.000397385,0.00004465826,0.0002299723,0.00000415365,0.0004869646,0.00005083201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005748646,"about_ca_system_score_gemma":0.0000564718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001873818,"about_ca_topic_score_gemma":0.00009127089,"domain_scores_codex":[0.9983906,0.0001793372,0.0002351305,0.0004658613,0.0003733067,0.0003558007],"domain_scores_gemma":[0.9988675,0.0002940804,0.0001238408,0.0003524751,0.0001813188,0.000180787],"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":[0.00009387056,0.00009799873,0.0009534135,0.000009233639,0.00003210753,0.000004863141,0.001453815,0.8857215,0.00009288268,0.0002112985,0.0001292262,0.1111998],"study_design_scores_gemma":[0.001380918,0.0006546086,0.000340801,0.00003759274,0.00003502464,0.00002477351,0.0001431621,0.9838393,0.002272621,0.0001621365,0.01082132,0.000287759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01940825,0.00006367499,0.977851,0.0004513323,0.0003945696,0.0002234811,0.000001681649,0.0004325222,0.001173482],"genre_scores_gemma":[0.927817,0.00002231167,0.06495845,0.00008322777,0.00008833245,0.00005047825,0.000006352682,0.00003762385,0.006936149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9128926,"threshold_uncertainty_score":0.7784234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05347264596570197,"score_gpt":0.2781317548242277,"score_spread":0.2246591088585257,"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."}}