{"id":"W2904464104","doi":"10.1609/aaai.v33i01.33013248","title":"Deep Convolutional Sum-Product Networks","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Convolutional neural network; Pooling; Computer science; Inference; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Probabilistic logic; Differentiable function; Benchmark (surveying); Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004941234,0.0002342792,0.0002813435,0.00008371686,0.0001870873,0.0002441445,0.001968222,0.0000762555,0.0002045656],"category_scores_gemma":[0.0002091129,0.0001727224,0.0001544518,0.0006254741,0.0002249455,0.0005356713,0.0004416258,0.0002960167,0.0002611312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004297596,"about_ca_system_score_gemma":0.00008031709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002636776,"about_ca_topic_score_gemma":0.000007073896,"domain_scores_codex":[0.9980356,0.00002809177,0.0004544182,0.0006092565,0.0004662391,0.0004064038],"domain_scores_gemma":[0.9983795,0.000106406,0.0003184177,0.0004026298,0.0007068363,0.00008624022],"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":[0.00004444125,0.0001023766,0.0007363465,0.00001552264,0.00002764064,2.653708e-7,0.0002758364,0.01345121,0.01850974,0.9252744,0.0005541391,0.04100813],"study_design_scores_gemma":[0.00002788408,0.0001132475,0.0006034035,0.00008199002,0.000009025262,0.000003300059,0.0001218,0.8072956,0.1466471,0.04457551,0.0002862872,0.0002348619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05201299,0.0002068459,0.8972853,0.007098137,0.003301085,0.001072098,0.000003670109,0.0001718856,0.03884794],"genre_scores_gemma":[0.9937527,0.00003916188,0.005104122,0.0002998049,0.0002118358,0.00001421767,5.745822e-7,0.00001068079,0.0005669548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9417397,"threshold_uncertainty_score":0.7043417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03965008146062683,"score_gpt":0.2524805903209098,"score_spread":0.212830508860283,"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."}}