{"id":"W4212932240","doi":"10.36227/techrxiv.14233652.v1","title":"Stochastic Dividers for Low Latency Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Error Correcting Code Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministerio de Ciencia e Innovación; National Natural Science Foundation of China; University of Alberta; New Mexico State University; National Science Foundation","keywords":"Stochastic computing; Computer science; Arithmetic; Latency (audio); Computation; Artificial neural network; Parallel computing; Algorithm; Mathematics; Artificial intelligence; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003713794,0.0003593597,0.0004129586,0.0001312298,0.000117768,0.0005807992,0.002024751,0.0003449089,0.00001530872],"category_scores_gemma":[0.0002001635,0.000355226,0.0003158839,0.000225341,0.00003538636,0.0002328433,0.003177571,0.000764882,0.000002390716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008874758,"about_ca_system_score_gemma":0.0001506713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000125922,"about_ca_topic_score_gemma":0.0001351596,"domain_scores_codex":[0.9977287,0.00007599562,0.0003830544,0.001047307,0.0002600151,0.0005049104],"domain_scores_gemma":[0.9975826,0.0003865867,0.0002118667,0.001442769,0.0002631977,0.0001130491],"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":[0.0000147146,0.000200587,0.0003205824,0.0004300123,0.0001608487,0.00006886037,0.001641286,0.8384889,0.00007691692,0.008875608,0.01398227,0.1357394],"study_design_scores_gemma":[0.00008534601,0.00004868787,0.0001115595,0.0001693823,0.00001672358,0.00001286555,0.0000184546,0.9936381,0.0001254962,0.005345788,0.00001741487,0.0004101998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002588936,0.0002952498,0.9891306,0.0008236215,0.003889558,0.0007641076,0.000001804064,0.002051771,0.0004543689],"genre_scores_gemma":[0.7775416,0.000006583327,0.221002,0.0005402298,0.0002016513,0.0002563022,0.00002115492,0.00003517441,0.000395333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7749527,"threshold_uncertainty_score":0.99989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02556206762920833,"score_gpt":0.2759428180004124,"score_spread":0.2503807503712041,"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."}}