{"id":"W2786618695","doi":"10.1109/fpt.2017.8280150","title":"FPGA-based training of convolutional neural networks with a reduced precision floating-point library","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Adder; Convolutional neural network; Computer science; Field-programmable gate array; Floating point; Double-precision floating-point format; Lookup table; IEEE floating point; Single-precision floating-point format; Artificial neural network; Artificial intelligence; Bandwidth (computing); Computer hardware; Parallel computing; Algorithm; Latency (audio)","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":[],"consensus_categories":[],"category_scores_codex":[0.0001100773,0.0001452433,0.0001864232,0.00005180015,0.0004192546,0.0001512623,0.00123855,0.00004965306,0.00003062453],"category_scores_gemma":[0.00004200845,0.0001142165,0.00005753902,0.0001880586,0.0001705559,0.001177027,0.0002844449,0.0001642451,0.000003200256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001244538,"about_ca_system_score_gemma":0.00009604965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005559003,"about_ca_topic_score_gemma":0.00000395014,"domain_scores_codex":[0.9987695,0.00003974983,0.0002719667,0.0004071094,0.0002405127,0.0002711408],"domain_scores_gemma":[0.9981553,0.0002524364,0.000339662,0.001076582,0.00006536818,0.0001106272],"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":[0.0001564318,0.0001474862,0.001653121,0.00001483626,0.00002767585,0.00001587555,0.0002973779,0.711177,0.003286457,0.08292878,0.002349859,0.1979451],"study_design_scores_gemma":[0.0004766889,0.0001209124,0.006126243,0.00004305112,0.000003948278,0.00001181142,0.00000966265,0.9862113,0.004448043,0.002185542,0.0002081486,0.0001546218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03508422,0.00003002966,0.9584365,0.002743467,0.00011721,0.0002755346,0.000002273781,0.000224723,0.00308608],"genre_scores_gemma":[0.7400315,0.000001814912,0.2594543,0.0002535858,0.0000802146,0.0000197751,0.000005774679,0.00001161075,0.0001414106],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7049474,"threshold_uncertainty_score":0.4657614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03390554162329246,"score_gpt":0.2668299662184518,"score_spread":0.2329244245951593,"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."}}