{"id":"W2893437765","doi":"10.48550/arxiv.1809.11086","title":"Learning Recurrent Binary/Ternary Weights","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Ternary operation; Recurrent neural network; Speedup; Binary number; Application-specific integrated circuit; Inference; Sequence (biology); Throughput; Identification (biology); Parallel computing; Algorithm; Computer engineering; Computer hardware; Artificial intelligence; Artificial neural network; Arithmetic; Programming language; Operating system","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":[0.000424767,0.0008424846,0.000504949,0.0005991811,0.0002874619,0.0008981627,0.001160121,0.0006953371,0.003597315],"category_scores_gemma":[0.003301126,0.0004069516,0.0004908141,0.0005945703,0.0003280174,0.001768338,0.0007526958,0.0009511464,0.001381244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005321299,"about_ca_system_score_gemma":0.0008283668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003599811,"about_ca_topic_score_gemma":0.006305106,"domain_scores_codex":[0.9996918,0.00003176736,0.00002555085,0.0001046034,0.0000955678,0.00005075476],"domain_scores_gemma":[0.9993649,0.0002048745,0.00008149672,0.0001257286,0.0001886274,0.00003445737],"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":[0.0003366445,0.0001436455,0.002983886,0.0002523492,0.0001384826,0.0003204112,0.0001802526,0.2919346,0.07082332,0.0262375,0.01015691,0.596492],"study_design_scores_gemma":[0.000009156668,0.00002648779,0.0002848893,0.000008513183,0.00002101164,0.00005155676,0.00001591782,0.9724139,0.01803701,0.00753801,0.001583536,0.00001005315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07873135,0.0002955415,0.9112539,0.0002557079,0.0001948475,0.00004692464,0.0003689874,0.0048518,0.004000978],"genre_scores_gemma":[0.6926734,0.0002890319,0.2984519,0.000246761,0.0001099322,0.0001100391,0.0008776092,0.0003614661,0.006879807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003599811,"threshold_uncertainty_score":0.01203424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07755215751959647,"score_gpt":0.1936445762296969,"score_spread":0.1160924187101005,"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."}}