{"id":"W4388930993","doi":"10.20944/preprints202311.1420.v1","title":"FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Field-programmable gate array; Computer science; MNIST database; Artificial neural network; Implementation; Convolutional neural network; Contextual image classification; Artificial intelligence; VHDL; Machine learning; Inference; Resource (disambiguation); Computer engineering; Image (mathematics); Embedded system","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":[0.0001801802,0.0003289325,0.0001549478,0.0002430866,0.0001289328,0.000474977,0.0006532821,0.000253063,0.003981859],"category_scores_gemma":[0.000558797,0.0001171629,0.0001500029,0.000250989,0.0001391451,0.0004770494,0.0002092972,0.0003452506,0.0008953434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000389143,"about_ca_system_score_gemma":0.0004190862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003400028,"about_ca_topic_score_gemma":0.004594252,"domain_scores_codex":[0.9998913,0.00002109584,0.000006936199,0.00002453266,0.00004136345,0.00001483499],"domain_scores_gemma":[0.9998525,0.00004012324,0.00001360636,0.00003151959,0.00005575035,0.000006449793],"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":[0.0004189424,0.0001409014,0.003215559,0.0003036753,0.00009318389,0.0003420305,0.0001166057,0.2597276,0.07017316,0.01990012,0.009477992,0.6360903],"study_design_scores_gemma":[0.00001819821,0.0001035512,0.0007264885,0.00001668175,0.00001302168,0.000131102,0.00001965224,0.9684673,0.02204016,0.001745268,0.006706783,0.00001175145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06234022,0.000423557,0.9216259,0.0002497359,0.0001882014,0.00007256531,0.0001648138,0.003390795,0.01154427],"genre_scores_gemma":[0.7445531,0.0003080696,0.2493247,0.0001357772,0.00003029866,0.00008931739,0.000306091,0.00006346484,0.005189098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003981859,"threshold_uncertainty_score":0.01332062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1987168277990281,"score_gpt":0.3936007438431155,"score_spread":0.1948839160440874,"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."}}