{"id":"W4387369393","doi":"10.1016/j.patcog.2023.109992","title":"Matrix randomized autoencoder","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Fundamental Research Funds for the Provincial Universities of Zhejiang; National Key Research and Development Program of China; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Autoencoder; Computer science; Scalar (mathematics); Matrix (chemical analysis); Representation (politics); Column (typography); Code (set theory); Class (philosophy); Pattern recognition (psychology); Tensor (intrinsic definition); Algorithm; Artificial intelligence; Mathematics; Deep learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007023388,0.00008386926,0.0001615855,0.0001445913,0.00008506921,0.0001058873,0.0002230581,0.00003921734,0.000145598],"category_scores_gemma":[0.0001110602,0.00007188317,0.00009037507,0.0003152721,0.0000168124,0.0001793713,0.0000862042,0.00008538222,0.006754402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009518159,"about_ca_system_score_gemma":0.00001076136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000727526,"about_ca_topic_score_gemma":0.000003838581,"domain_scores_codex":[0.999045,0.0001953804,0.0001633151,0.0002266824,0.0001710747,0.0001985692],"domain_scores_gemma":[0.9994577,0.000203316,0.00006144292,0.0001921939,0.00003794237,0.00004740361],"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":[0.0001176188,0.00001904548,0.0002919682,0.00002106747,0.0000173248,0.00001922621,0.000510778,0.0001104983,0.00003563456,0.000131475,0.003499669,0.9952257],"study_design_scores_gemma":[0.02345406,0.00002400995,0.001938951,0.00004434538,0.00001339297,0.00001851798,0.00001416405,0.9554693,0.0001900066,0.01624821,0.002364638,0.000220361],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06038128,0.00002337493,0.9296736,0.00302961,0.0006568357,0.0001894742,0.000003883555,0.001273865,0.004768115],"genre_scores_gemma":[0.9870827,0.0000586329,0.009102368,0.0008600084,0.0002341138,0.0001100157,0.000106511,0.00001831506,0.00242735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9950053,"threshold_uncertainty_score":0.994019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02164062769398055,"score_gpt":0.2823863829962465,"score_spread":0.260745755302266,"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."}}