{"id":"W1579122361","doi":"10.1109/ijcnn.2005.1556042","title":"Learning nonlinear constraints with contrastive backpropagation","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Backpropagation; Independence (probability theory); Computer science; Representation (politics); Nonlinear system; Artificial intelligence; Artificial neural network; Machine learning; Energy (signal processing); Algorithm; Pattern recognition (psychology); Mathematics","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":[0.0002994819,0.0004721903,0.0003751038,0.0002417754,0.0002561403,0.00100521,0.0009628915,0.0001579561,0.0002615392],"category_scores_gemma":[0.00004993721,0.0003931183,0.0001004312,0.000309298,0.000279546,0.001289229,0.0001066765,0.0007560987,0.00009693257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000159063,"about_ca_system_score_gemma":0.0001584812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002777878,"about_ca_topic_score_gemma":0.00003685533,"domain_scores_codex":[0.9968176,0.00002857908,0.0006131,0.0009094348,0.0008156295,0.0008156393],"domain_scores_gemma":[0.9981428,0.00006098084,0.0005460776,0.0001689803,0.0008624768,0.0002187135],"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":[0.0007195885,0.00118696,0.01255758,0.0001302806,0.0003313255,0.0003095467,0.0004999106,0.07574812,0.006929545,0.7248089,0.01748928,0.159289],"study_design_scores_gemma":[0.001016802,0.000387299,0.003363827,0.0002997924,0.00001642358,0.0001979553,0.00007539918,0.9879368,0.002053831,0.002191442,0.001840114,0.0006203483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05053389,0.00009200395,0.8587647,0.009839261,0.001827898,0.0009329969,0.00002643893,0.0009190164,0.07706378],"genre_scores_gemma":[0.9856867,0.00008767219,0.01134549,0.0005222968,0.0009305172,0.00005192727,0.00003310377,0.00003157079,0.001310744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9351528,"threshold_uncertainty_score":0.9998521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.018024568077374,"score_gpt":0.2356152527498275,"score_spread":0.2175906846724535,"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."}}