{"id":"W2166734522","doi":"10.1007/0-387-28487-7_2","title":"On the Arithmetic Precision for Implementing Back-Propagation Networks on FPGA: A Case Study","year":2006,"lang":"en","type":"book-chapter","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Field-programmable gate array; Computer science; Floating point; Quantization (signal processing); Artificial neural network; Fixed-point arithmetic; Point (geometry); Single-precision floating-point format; Perceptron; Computer engineering; Fixed point; Multilayer perceptron; Parallel computing; Computer hardware; Algorithm; Artificial intelligence; Mathematics","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":[0.001076511,0.000793246,0.0002953105,0.0005885693,0.0004507812,0.002142914,0.001573816,0.001175291,0.006500662],"category_scores_gemma":[0.004762903,0.0003425448,0.0002681408,0.001362526,0.000567488,0.002597712,0.0004985784,0.001247901,0.0009529745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008560034,"about_ca_system_score_gemma":0.0006291509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003362885,"about_ca_topic_score_gemma":0.004782196,"domain_scores_codex":[0.9992822,0.0001988648,0.00006429271,0.0000765037,0.0002745693,0.0001036143],"domain_scores_gemma":[0.9974148,0.001779805,0.0001155358,0.0002758929,0.0003851492,0.00002881056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008098392,0.0001933426,0.003823172,0.001112588,0.00006623063,0.003524564,0.0008701088,0.1066795,0.03318935,0.1147799,0.008877967,0.7260734],"study_design_scores_gemma":[0.0002631486,0.00146373,0.003568876,0.0007888705,0.0003595248,0.008418689,0.001424902,0.5754823,0.2008191,0.09553213,0.1117569,0.0001216774],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3653485,0.01410634,0.4891206,0.002850165,0.0003772005,0.0002314538,0.0002668317,0.002277514,0.1254215],"genre_scores_gemma":[0.8021463,0.003239907,0.177544,0.0002187599,0.00007246199,0.00004778855,0.0001247687,0.0002503559,0.01635569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006500662,"threshold_uncertainty_score":0.02174687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04634688288532828,"score_gpt":0.2833551298389025,"score_spread":0.2370082469535742,"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."}}