{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002076778,0.001364519,0.001116513,0.0008018249,0.0004574711,0.001149433,0.002770096,0.002196373,0.00189696],"category_scores_gemma":[0.01377105,0.001254943,0.0009679561,0.001017672,0.001391946,0.003360594,0.002182659,0.002994376,0.0004460955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001762286,"about_ca_system_score_gemma":0.001365019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00935643,"about_ca_topic_score_gemma":0.01052715,"domain_scores_codex":[0.999155,0.00028793,0.00005411463,0.0002071071,0.0002361217,0.0000597226],"domain_scores_gemma":[0.9963892,0.002502176,0.0003056788,0.0004107601,0.0003158872,0.00007637336],"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":[0.00007275857,0.00004084855,0.0006060448,0.00005447838,0.00005765241,0.00007583986,0.00006535972,0.935107,0.001722628,0.02429151,0.001010826,0.03689502],"study_design_scores_gemma":[0.000003744421,0.00000383032,0.00002524595,0.00000206678,0.000001283601,0.000005014935,0.000001634728,0.9933434,0.0002669352,0.006246532,0.00009825824,0.000002020852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01083058,0.00004799984,0.9879137,0.0001655754,0.00001056749,0.00002911829,0.00005294202,0.0004156503,0.0005338356],"genre_scores_gemma":[0.4762783,0.000139396,0.5199834,0.0003725832,0.00004715504,0.0003967728,0.0004857115,0.000226129,0.002070548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00935643,"threshold_uncertainty_score":0.01860398,"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."}}