{"id":"W2981710180","doi":"10.48550/arxiv.1910.12151","title":"Making Predictive Coding Networks Generative","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"MNIST database; Computer science; Predictive coding; Artificial neural network; Generative grammar; Discriminative model; Artificial intelligence; Reciprocal; Hierarchy; Backpropagation; Coding (social sciences); Nonlinear system; Machine learning; Class (philosophy); Simple (philosophy); 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":[0.001297789,0.0006257533,0.0005063477,0.0004909461,0.0004621965,0.001431361,0.001306397,0.001119256,0.004177812],"category_scores_gemma":[0.00915218,0.0005734441,0.0005260838,0.0003907182,0.00226439,0.002348699,0.002285435,0.002486777,0.0008159217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008443507,"about_ca_system_score_gemma":0.0006567189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001431894,"about_ca_topic_score_gemma":0.002137196,"domain_scores_codex":[0.9994873,0.0001348713,0.00001979835,0.0001468298,0.0001451363,0.00006609735],"domain_scores_gemma":[0.997458,0.001596038,0.0001324079,0.0005078414,0.0002167908,0.00008882376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001378673,0.00004945991,0.001037758,0.0001005339,0.00004462883,0.0001627006,0.0003559889,0.5462599,0.0127857,0.3295873,0.004105731,0.1053723],"study_design_scores_gemma":[0.00001545728,0.00001499336,0.0001024994,0.00001838482,0.00001098046,0.00003910941,0.00002107009,0.8563808,0.002995054,0.1382907,0.002100405,0.00001053874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03280567,0.0001929247,0.9569613,0.0006966494,0.00009822292,0.00004509316,0.00009448818,0.0008566172,0.008249069],"genre_scores_gemma":[0.7877219,0.000371522,0.201846,0.0006461046,0.000162225,0.0001483959,0.0003000446,0.0006277977,0.008175916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004177812,"threshold_uncertainty_score":0.01397616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1312230308254807,"score_gpt":0.2133092003186279,"score_spread":0.08208616949314723,"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."}}