{"id":"W2294245963","doi":"10.21437/interspeech.2014-82","title":"Manifold regularized deep neural networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial neural network; Bottleneck; Discriminative model; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Locality; Regularization (linguistics); Deep learning; Context (archaeology); Feature vector; Deep neural networks","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":[0.0002112043,0.00007690831,0.00009729945,0.00004420053,0.0000668038,0.0001406676,0.0004416566,0.00004617211,0.000344043],"category_scores_gemma":[0.00003918465,0.00006223685,0.00006105861,0.0001481192,0.00001047141,0.000187846,0.00009050125,0.00006088941,0.0001915669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007101179,"about_ca_system_score_gemma":0.00000278226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008436828,"about_ca_topic_score_gemma":0.00001441421,"domain_scores_codex":[0.9992791,0.00007131013,0.0001168667,0.0002132783,0.0001297488,0.0001896683],"domain_scores_gemma":[0.9993828,0.0001066488,0.00002922047,0.0003646286,0.0000327788,0.0000839234],"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":[0.00000278639,0.00002256151,0.0001074547,0.000001536203,0.000007043402,0.000005884646,0.00002323299,0.00006020091,0.0001429512,0.1651562,0.001449393,0.8330208],"study_design_scores_gemma":[0.0001723685,0.00001765837,0.0008767339,0.000001480979,0.000002202638,0.00001921391,0.00000387987,0.9917459,0.0006933468,0.003106753,0.0032599,0.0001005023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001388475,0.000009466906,0.9352083,0.001079862,0.0002952034,0.00004651436,4.290844e-8,0.0002842257,0.06168796],"genre_scores_gemma":[0.8232937,0.00000257209,0.1717002,0.003224079,0.0001262485,0.000006748588,9.222963e-7,0.000006347748,0.001639121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9916857,"threshold_uncertainty_score":0.376703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01104771283005819,"score_gpt":0.2031877847558959,"score_spread":0.1921400719258377,"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."}}