{"id":"W1964812476","doi":"10.1109/taslp.2014.2303296","title":"Application of Deep Belief Networks for Natural Language Understanding","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":460,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Deep belief network; Artificial intelligence; Computer science; Support vector machine; Boosting (machine learning); Artificial neural network; Machine learning; Deep learning; Principle of maximum entropy; Backpropagation; Pattern recognition (psychology)","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":[0.0003312266,0.0001967862,0.0002448529,0.00016376,0.0004087475,0.0001734108,0.0003883158,0.0001011881,0.000006226889],"category_scores_gemma":[0.0000378137,0.000179705,0.0000802561,0.0004014425,0.00007831167,0.0004256805,0.00001114393,0.0002257252,0.000001588339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005241065,"about_ca_system_score_gemma":0.00003409975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002148545,"about_ca_topic_score_gemma":0.0000527072,"domain_scores_codex":[0.9987231,0.00003405166,0.0002742607,0.0004355256,0.000209415,0.0003235799],"domain_scores_gemma":[0.9991093,0.0001931465,0.0001936787,0.0003458905,0.00006694461,0.00009100488],"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":[0.00002573893,0.00004920567,0.00002115573,0.0002154994,0.0000149069,0.000001679046,0.002793928,0.0009877875,0.005823479,0.0002195491,0.00001128729,0.9898358],"study_design_scores_gemma":[0.001064341,0.0001319688,0.00008262472,0.0002831789,0.00005813342,0.00004304103,0.001775335,0.9517795,0.04296726,0.001282358,0.0001315341,0.0004006962],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008386606,0.002279979,0.9881622,0.000329905,0.0001857396,0.0002430367,0.000003049397,0.0001731572,0.0002363561],"genre_scores_gemma":[0.9180419,0.00001505095,0.08118219,0.0004780634,0.0001340466,0.00003205657,0.000005416641,0.00002052698,0.00009078223],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9894351,"threshold_uncertainty_score":0.7328158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01281846356590224,"score_gpt":0.2571697326409619,"score_spread":0.2443512690750596,"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."}}