{"id":"W2141473882","doi":"","title":"Shallow vs. Deep Sum-Product Networks","year":2011,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep learning; Product (mathematics); Computer science; Artificial neural network; Artificial intelligence; Deep neural networks; Computation; Layer (electronics); Deep water; Theoretical computer science; Mathematics; Algorithm; Engineering","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":[0.000367648,0.0001461543,0.000148223,0.00006486462,0.0001352406,0.00007420173,0.001322208,0.00005560583,0.0003536163],"category_scores_gemma":[0.00009150132,0.0001268198,0.00006001687,0.0003354432,0.00004475883,0.0005549322,0.0005583463,0.0002720846,0.0001855858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002433531,"about_ca_system_score_gemma":0.00002388081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000137696,"about_ca_topic_score_gemma":0.00004882039,"domain_scores_codex":[0.998702,0.00007864525,0.0001794046,0.0004755698,0.0001966924,0.0003677041],"domain_scores_gemma":[0.9989451,0.00005219605,0.000067293,0.0007806289,0.00005533297,0.00009945989],"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":[0.00003935963,0.000152692,0.06006783,0.00001516067,0.00006933336,0.0001420075,0.003104197,0.08727185,0.00003738443,0.6524526,0.003633615,0.193014],"study_design_scores_gemma":[0.0002130955,0.0000529937,0.02205608,0.000006198334,0.000006130525,0.00001862782,0.00001968995,0.9715977,0.0001412799,0.00313319,0.002472161,0.0002828621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001249659,0.00007834078,0.9256109,0.0003066626,0.0008971949,0.00008326343,3.578811e-8,0.0004483982,0.07132555],"genre_scores_gemma":[0.7301266,0.000006302614,0.2681106,0.0004704878,0.0002114507,0.000004745045,7.480838e-7,0.0000113231,0.001057664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8843259,"threshold_uncertainty_score":0.5171563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02377801740260188,"score_gpt":0.23183415635814,"score_spread":0.2080561389555381,"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."}}