{"id":"W3161204726","doi":"10.1109/icfpt51103.2020.00017","title":"From TensorFlow Graphs to LUTs and Wires: Automated Sparse and Physically Aware CNN Hardware Generation","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Field-programmable gate array; Computer hardware; Convolutional neural network; Throughput; Parallel computing; Embedded system; Computer engineering; Computer architecture; Artificial intelligence","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":[0.0002752686,0.0008562963,0.0002936297,0.0005581154,0.0003802329,0.0006801653,0.001340444,0.0003000634,0.005681547],"category_scores_gemma":[0.0009514753,0.0004274604,0.0005716869,0.0004303751,0.000488076,0.001398191,0.000855621,0.0006779862,0.00115702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010046,"about_ca_system_score_gemma":0.001580233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004552542,"about_ca_topic_score_gemma":0.01254679,"domain_scores_codex":[0.9998003,0.00002557327,0.00001240046,0.00004313123,0.00008240775,0.00003624173],"domain_scores_gemma":[0.9996639,0.00008435661,0.00004215649,0.0001124222,0.00007639569,0.00002075742],"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":[0.0002277721,0.0001371491,0.002402725,0.0003386174,0.0000568492,0.000319378,0.000242572,0.376525,0.07520663,0.07150345,0.02019067,0.4528491],"study_design_scores_gemma":[0.00002360952,0.0001011827,0.0002744139,0.00002512017,0.00001600984,0.00007353169,0.0000374806,0.9294906,0.03896258,0.01959753,0.01137473,0.00002314342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03936766,0.0002453471,0.9387469,0.0003373703,0.0001204097,0.0001155622,0.0003563052,0.01080351,0.009906885],"genre_scores_gemma":[0.4499325,0.0002471264,0.5408981,0.0002217059,0.00003116531,0.0001930321,0.0009137418,0.001055967,0.006506769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005681547,"threshold_uncertainty_score":0.01900667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02715652103885282,"score_gpt":0.2319514483480878,"score_spread":0.2047949273092349,"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."}}