{"id":"W4200561385","doi":"10.18280/ria.350610","title":"Optimization of the Convolution Operation to Accelerate Deep Neural Networks in FPGA","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Loop unrolling; Computer science; Convolution (computer science); Field-programmable gate array; Computation; Convolutional neural network; Parallel computing; Gate array; Speedup; MATLAB; Artificial neural network; Pixel; Deep learning; Artificial intelligence; Process (computing); Computer hardware; Algorithm; Compiler","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009381508,0.00007886611,0.0001018475,0.0000404919,0.00004371366,0.00003321837,0.0001098859,0.00004080475,0.0001065347],"category_scores_gemma":[0.00004978429,0.00007378466,0.00003839381,0.0005200037,0.0000202047,0.00009048497,0.00003153881,0.0001122829,0.00001504935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004379482,"about_ca_system_score_gemma":0.000008301446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001372318,"about_ca_topic_score_gemma":0.00007981374,"domain_scores_codex":[0.9993437,0.00003615295,0.0002669739,0.0001344664,0.00006648092,0.0001522039],"domain_scores_gemma":[0.9996315,0.00002968709,0.00002281757,0.000219328,0.00006877516,0.00002788174],"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":[0.00000264821,0.000014685,0.0003208817,0.00001465809,0.000002618338,0.0000017474,0.0005070867,0.9854027,0.005593067,0.0001465218,0.00005323719,0.007940132],"study_design_scores_gemma":[0.00001795339,0.000006223866,0.0002342419,0.0000337649,0.000003327472,0.00000492597,0.0002818745,0.8924289,0.1067777,0.00001855887,0.0001201635,0.00007240489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2283172,0.0003648662,0.7690746,0.0004716681,0.0006415049,0.0001796975,0.00000148799,0.00005358529,0.0008953299],"genre_scores_gemma":[0.9989235,0.0000546723,0.0007131984,0.0000909081,0.00004654767,0.000008093009,0.00000679612,0.00001317795,0.0001430955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7706063,"threshold_uncertainty_score":0.3008851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02138946356776802,"score_gpt":0.233201725623482,"score_spread":0.211812262055714,"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."}}