{"id":"W4391455314","doi":"10.1109/icfpt59805.2023.00065","title":"Journal Track Paper ICFPT 2023 : HyBNN: Quantifying and Optimizing Hardware Efficiency of Binary Neural Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Quantization (signal processing); Floating point; Computer hardware; Overhead (engineering); Hardware acceleration; Deep learning; Binary number; Artificial neural network; Convolution (computer science); Computer engineering; FLOPS; Algorithm; Artificial intelligence; Field-programmable gate array; Parallel computing; Mathematics; Arithmetic","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":[0.001811848,0.001638986,0.000775066,0.00092274,0.0005686851,0.002597999,0.002229134,0.001376148,0.04021599],"category_scores_gemma":[0.004622775,0.0003538665,0.0005175449,0.001183278,0.0005232039,0.003673685,0.001167742,0.001791535,0.01356615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001642758,"about_ca_system_score_gemma":0.002481749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007422345,"about_ca_topic_score_gemma":0.01172317,"domain_scores_codex":[0.9988594,0.0001472203,0.00005562024,0.000225553,0.0005542075,0.000158027],"domain_scores_gemma":[0.9986985,0.0002989398,0.00007985343,0.0002690991,0.000514962,0.0001386613],"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":[0.0009225808,0.0002608883,0.002178535,0.000638261,0.0001459611,0.0001635326,0.00004724778,0.08521055,0.02038657,0.01865245,0.2850372,0.5863563],"study_design_scores_gemma":[0.0002564707,0.0009009808,0.00212899,0.0001919979,0.00009832693,0.0002596402,0.00004893451,0.6752043,0.04126442,0.01853659,0.2610212,0.00008813313],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1067811,0.01581181,0.5615554,0.007082211,0.009892322,0.001034859,0.01219455,0.04651585,0.2391318],"genre_scores_gemma":[0.4049535,0.0087665,0.3740672,0.002547288,0.00172126,0.0009874875,0.04141806,0.008229215,0.1573095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04021599,"threshold_uncertainty_score":0.1345359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04487813046640042,"score_gpt":0.2957625617326771,"score_spread":0.2508844312662766,"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."}}