{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002576094,0.0003330181,0.0003048689,0.0002993213,0.0002344897,0.0001426015,0.002517848,0.0002879064,0.0000610264],"category_scores_gemma":[0.00002621914,0.0003803778,0.0002161393,0.0003463938,0.00009021061,0.0003799039,0.004168067,0.0009193909,0.0003639336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002329789,"about_ca_system_score_gemma":0.0001725039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008814232,"about_ca_topic_score_gemma":0.000009283351,"domain_scores_codex":[0.9975728,0.00019739,0.0002192053,0.001457787,0.0001304422,0.0004223782],"domain_scores_gemma":[0.9978827,0.000063845,0.0002640169,0.001445283,0.0001545768,0.0001895606],"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":[0.00009488322,0.0003779932,0.0217623,0.0003572068,0.0003446477,0.002618472,0.002740851,0.6151812,0.0000761669,0.3349719,0.002382717,0.01909169],"study_design_scores_gemma":[0.0002348452,0.0001201357,0.0006377568,0.0001811436,0.00002816234,0.000006705274,0.00002546432,0.9567807,0.00004409357,0.03781512,0.003675464,0.0004503458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4358658,0.00008438859,0.5578253,0.00009283026,0.001570865,0.0001488042,0.000001821635,0.00037874,0.004031373],"genre_scores_gemma":[0.9879094,0.0001997395,0.007628154,0.00005305327,0.0003241147,7.435817e-7,0.000009355823,0.0000197544,0.003855688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5520436,"threshold_uncertainty_score":0.9998648,"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."}}