{"id":"W2178103884","doi":"10.48550/arxiv.1511.08400","title":"Regularizing RNNs by Stabilizing Activations","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Air Force Research Laboratory; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; U.S. Department of Defense","keywords":"Recurrent neural network; TIMIT; Computer science; Term (time); Dropout (neural networks); Speech recognition; Task (project management); Language model; Artificial intelligence; Artificial neural network; Machine learning; Hidden Markov model","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":[0.00110823,0.001427359,0.0005523794,0.0003925409,0.0004165292,0.000748106,0.001402016,0.0008845882,0.002218786],"category_scores_gemma":[0.004862304,0.0004565768,0.000487756,0.0003351168,0.000695153,0.001100593,0.001121113,0.001618778,0.001604757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006858053,"about_ca_system_score_gemma":0.0009815529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003656034,"about_ca_topic_score_gemma":0.006037924,"domain_scores_codex":[0.99944,0.000119774,0.00004206544,0.0001958617,0.0001363978,0.00006586581],"domain_scores_gemma":[0.9989196,0.000353469,0.000127221,0.0002457586,0.0003099569,0.00004402853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001311925,0.00007003929,0.001170545,0.00008350673,0.00006509164,0.00009606288,0.0001049163,0.8411965,0.04289747,0.009808319,0.002912419,0.1014639],"study_design_scores_gemma":[0.000005295406,0.00002205176,0.0000892703,0.000005038476,0.000006223041,0.00001447712,0.000006485667,0.9902455,0.006514652,0.002476053,0.0006104173,0.000004577314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03615275,0.0002061397,0.9583865,0.0001860787,0.0001053552,0.00003663477,0.00008487643,0.002440621,0.002400941],"genre_scores_gemma":[0.7222145,0.0002205325,0.2705501,0.0002731492,0.00008784802,0.0002072454,0.0004069112,0.0007534975,0.005286265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003656034,"threshold_uncertainty_score":0.007422566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1401149921742679,"score_gpt":0.1975755539048891,"score_spread":0.05746056173062122,"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."}}