{"id":"W2775300540","doi":"10.1609/aaai.v32i1.12111","title":"RelNN: A Deep Neural Model for Relational Learning","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistical relational learning; Computer science; Artificial intelligence; Deep learning; Scalability; Machine learning; Object (grammar); Artificial neural network; Modular design; Focus (optics); Deep belief network; Architecture; Relational database; Data mining","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":[0.0008453827,0.0007082036,0.0006338964,0.0006229871,0.0002962205,0.001066013,0.002370258,0.000980478,0.003308348],"category_scores_gemma":[0.002829188,0.0005832796,0.0009100097,0.0009869072,0.0006281524,0.002745484,0.001290285,0.002476347,0.001225324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009865514,"about_ca_system_score_gemma":0.0009035682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008075941,"about_ca_topic_score_gemma":0.01296545,"domain_scores_codex":[0.9995441,0.0001025996,0.00002903608,0.0001504079,0.0001273179,0.0000464086],"domain_scores_gemma":[0.9994597,0.0002117099,0.00007131312,0.0001108486,0.0001121156,0.00003433552],"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":[0.0002166883,0.0001505441,0.002392811,0.0002994479,0.0002535646,0.0002379757,0.0001761845,0.5535567,0.005506353,0.1170473,0.01963794,0.3005244],"study_design_scores_gemma":[0.000008318744,0.00002023753,0.0001752916,0.00002002982,0.00001533378,0.00004199165,0.000009033625,0.9535958,0.0008417129,0.04141942,0.003843546,0.000009286845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009847299,0.0009491628,0.9817098,0.0006006392,0.00008891433,0.00004370625,0.001167931,0.002230334,0.003362214],"genre_scores_gemma":[0.452377,0.002289827,0.5234313,0.0009313882,0.0001406686,0.0002984707,0.006198998,0.0004426187,0.01388966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008075941,"threshold_uncertainty_score":0.01605791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1342475788295949,"score_gpt":0.3147651427810738,"score_spread":0.1805175639514789,"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."}}