{"id":"W4247198796","doi":"10.1109/micro.2016.7783722","title":"Stripes: Bit-serial deep neural network computing","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":329,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speedup; Energy (signal processing); Artificial neural network; Deep neural networks; Efficient energy use; Set (abstract data type); Variance (accounting); Representation (politics); Parallel computing; Computer engineering; Algorithm; Real-time computing; Artificial intelligence; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000369541,0.0006656906,0.0004010235,0.0005060138,0.0002597713,0.0008504081,0.002027772,0.0003877754,0.01763977],"category_scores_gemma":[0.001220603,0.0003048975,0.0002805106,0.0009654611,0.0003701446,0.001356155,0.001151732,0.001046949,0.003272018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005487716,"about_ca_system_score_gemma":0.0007027538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001562073,"about_ca_topic_score_gemma":0.003425749,"domain_scores_codex":[0.9997491,0.00003672039,0.00001673599,0.00004197705,0.0001251618,0.0000302959],"domain_scores_gemma":[0.999621,0.00009843033,0.00003216312,0.0001102438,0.00009365839,0.00004447986],"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":[0.002458906,0.000486283,0.003530826,0.0007714063,0.0002235566,0.0005270067,0.000187098,0.1153493,0.0654529,0.05199005,0.1685798,0.5904428],"study_design_scores_gemma":[0.000240023,0.0004314691,0.0008535396,0.00006632042,0.00004117147,0.0002139984,0.00004953135,0.880723,0.0333551,0.03680247,0.04717573,0.00004771085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09210949,0.002739881,0.8200103,0.001394423,0.001133814,0.0003123056,0.002405028,0.03854243,0.04135231],"genre_scores_gemma":[0.5446363,0.001535353,0.4129856,0.001208095,0.0002577504,0.0004679071,0.005502764,0.001520283,0.03188594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01763977,"threshold_uncertainty_score":0.05901086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01743468266604897,"score_gpt":0.2561888464617708,"score_spread":0.2387541637957218,"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."}}