{"id":"W3174237283","doi":"10.48550/arxiv.2106.10314","title":"Differentiable Particle Filtering without Modifying the Forward Pass","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Target Tracking and Data Fusion in Sensor Networks","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differentiable function; Resampling; Gradient descent; Particle filter; Estimator; Computer science; Algorithm; Overhead (engineering); Filter (signal processing); Backpropagation; Operator (biology); Mathematical optimization; Mathematics; Artificial intelligence; Artificial neural network; Statistics; Mathematical analysis","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":[0.0008442545,0.0007244397,0.000689064,0.0004965421,0.0003708597,0.001059737,0.0008031544,0.001403288,0.002959736],"category_scores_gemma":[0.00371974,0.0004522372,0.0006568788,0.0006184363,0.0007408854,0.001249103,0.0007717697,0.001730511,0.001776159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006487908,"about_ca_system_score_gemma":0.0009754095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002803176,"about_ca_topic_score_gemma":0.003293584,"domain_scores_codex":[0.9994535,0.00009007076,0.0000366168,0.0001281831,0.0002516491,0.00004004806],"domain_scores_gemma":[0.99913,0.0003088916,0.00007331508,0.0003112115,0.000152686,0.00002389606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001753286,0.00009924089,0.001234123,0.0002872337,0.0001028783,0.0003266769,0.0002396931,0.3126523,0.06631766,0.1785652,0.00674679,0.433253],"study_design_scores_gemma":[0.0000157898,0.0000402595,0.0005026333,0.00001600444,0.00001783075,0.0001140182,0.00001265167,0.9486123,0.01828326,0.02361523,0.008745788,0.00002426781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001960731,0.00003645546,0.9965985,0.0000527331,0.000043574,0.00001224717,0.00002381734,0.0003057468,0.0009663131],"genre_scores_gemma":[0.145983,0.0002210463,0.8442546,0.0001892853,0.00007668279,0.0001039626,0.0001848617,0.0003221022,0.008664417],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002959736,"threshold_uncertainty_score":0.009901285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08250551561712702,"score_gpt":0.1904684330867409,"score_spread":0.1079629174696139,"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."}}