{"id":"W4415947855","doi":"10.48550/arxiv.2510.15930","title":"Implémentation Efficiente de Fonctions de Convolution sur FPGA à l'Aide de Blocs Paramétrables et d'Approximations Polynomiales","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Field-programmable gate array; Convolution (computer science); Convolutional neural network; Routing (electronic design automation); Resource (disambiguation); Artificial neural network; Selection (genetic algorithm)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001481195,0.00084241,0.0007400215,0.0007017407,0.0006139992,0.0002708063,0.0006392478,0.001038357,0.00009953763],"category_scores_gemma":[0.0004139204,0.001075275,0.000503473,0.0006683713,0.0002019156,0.0004138039,0.000298344,0.001527862,0.00006715907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002439676,"about_ca_system_score_gemma":0.001559728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002223176,"about_ca_topic_score_gemma":0.0004457178,"domain_scores_codex":[0.9957592,0.0005283334,0.001212883,0.0009011937,0.0003146682,0.001283726],"domain_scores_gemma":[0.9975259,0.0005490629,0.0003775386,0.0009492961,0.0002697559,0.0003284716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001662939,0.001311946,0.3280646,0.003113211,0.001588354,0.00004407142,0.008434598,0.4492221,0.1769131,0.008504845,0.009755234,0.01288168],"study_design_scores_gemma":[0.002336404,0.0002711046,0.2970413,0.002961197,0.001838349,0.0001599227,0.001875528,0.3315269,0.3470159,0.005655131,0.006591002,0.002727235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4821686,0.00099844,0.5117971,0.0004223088,0.0006691011,0.001014877,0.0002334858,0.0009635692,0.001732578],"genre_scores_gemma":[0.9684774,0.003126129,0.02497413,0.0003518451,0.0003473211,0.0009946225,0.0004807292,0.0001155405,0.001132311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4868229,"threshold_uncertainty_score":0.9991698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04718619128373706,"score_gpt":0.2901680122472983,"score_spread":0.2429818209635612,"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."}}