{"id":"W2103255058","doi":"","title":"Relative Density Nets: A New Way to Combine Backpropagation with HMM's","year":2001,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Discriminative model; Computer science; Backpropagation; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Feedforward neural network; Speech recognition; Feed forward; Point (geometry); Machine learning; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001967414,0.001519109,0.001090862,0.001063028,0.0004375596,0.001347074,0.002723686,0.001335224,0.004197994],"category_scores_gemma":[0.004823716,0.001085478,0.0008653891,0.001104461,0.0008026448,0.00335327,0.002090392,0.002483526,0.001943401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006760239,"about_ca_system_score_gemma":0.0008244943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004445433,"about_ca_topic_score_gemma":0.006182783,"domain_scores_codex":[0.9990906,0.0002348916,0.00005065771,0.0002027192,0.000353704,0.00006748369],"domain_scores_gemma":[0.9989192,0.0005497921,0.00007899674,0.0001504321,0.0002433863,0.00005819208],"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":[0.0002015273,0.0001954472,0.0008842724,0.0002458586,0.0003020812,0.00016764,0.0001652346,0.3287052,0.01007624,0.0408458,0.006217844,0.6119928],"study_design_scores_gemma":[0.00001168428,0.00003349121,0.0001030038,0.00001276118,0.00002132071,0.00003049622,0.000005504602,0.9834157,0.002768119,0.01121563,0.002367833,0.00001442793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001880337,0.0001937893,0.995404,0.00006647192,0.00007294569,0.00003319407,0.00003239521,0.001581898,0.0007350484],"genre_scores_gemma":[0.1045807,0.0005315527,0.887506,0.0002225587,0.000148667,0.0002060761,0.0002112855,0.0004724932,0.006120641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004445433,"threshold_uncertainty_score":0.01404363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01587924644970704,"score_gpt":0.2339953062531079,"score_spread":0.2181160598034009,"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."}}