{"id":"W2890008096","doi":"","title":"Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Recurrent neural network; Probabilistic logic; Artificial intelligence; Deep learning; Product (mathematics); Semantics (computer science); Inference; Representation (politics); Completeness (order theory); Theoretical computer science; Graphical model; Machine learning; Artificial neural network; Mathematics; Programming language","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":[0.002472055,0.001170134,0.001257572,0.0009474659,0.0006240234,0.001392139,0.002431305,0.001733362,0.00293324],"category_scores_gemma":[0.01289573,0.001018135,0.0009962261,0.0009124259,0.001321795,0.004810487,0.002028372,0.003120217,0.0007335047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001580045,"about_ca_system_score_gemma":0.001392412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003170571,"about_ca_topic_score_gemma":0.005743465,"domain_scores_codex":[0.999247,0.0002232364,0.00005907752,0.0002137889,0.0001906629,0.0000662656],"domain_scores_gemma":[0.9960955,0.002453704,0.0003143224,0.0004199377,0.0005801759,0.0001363936],"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":[0.0001327705,0.0001149681,0.0009605061,0.0002024964,0.0001057597,0.0001421788,0.0001961384,0.6828714,0.003598911,0.0961923,0.002618239,0.2128644],"study_design_scores_gemma":[0.000004792248,0.00001201187,0.00003314611,0.000006591409,0.000004332674,0.00001353307,0.00000431948,0.9691902,0.0004978915,0.03001718,0.0002124753,0.000003459042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01001526,0.0001857593,0.9882631,0.0001732004,0.00002276273,0.00003295411,0.0000692401,0.0004756443,0.0007621436],"genre_scores_gemma":[0.4795547,0.0004971722,0.513391,0.0002473986,0.00009553783,0.000300394,0.0008688066,0.0002782149,0.004766762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003170571,"threshold_uncertainty_score":0.01307362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02400853379914847,"score_gpt":0.2731631246584928,"score_spread":0.2491545908593443,"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."}}