{"id":"W4386914858","doi":"10.36227/techrxiv.24165294.v1","title":"A Power-efficient Image Classifier using Neural Network with Pipelined FFT Architecture","year":2023,"lang":"en","type":"preprint","venue":"","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; MNIST database; Fast Fourier transform; Memory footprint; Artificial neural network; Artificial intelligence; Classifier (UML); Computer engineering; Parallel computing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001599551,0.0004452632,0.0003224522,0.0003678525,0.0002994547,0.0004021816,0.0008797437,0.0004963606,0.002557246],"category_scores_gemma":[0.0003552572,0.0001792832,0.0002603026,0.0004722983,0.0002025104,0.0009529687,0.0002549486,0.0004020136,0.0006703936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006767304,"about_ca_system_score_gemma":0.0007657982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00745168,"about_ca_topic_score_gemma":0.01086483,"domain_scores_codex":[0.999864,0.000008543903,0.000008520372,0.00004131875,0.00005829507,0.00001941097],"domain_scores_gemma":[0.9998633,0.0000266113,0.00001101278,0.00002190203,0.00006901493,0.000008280286],"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":[0.0003056066,0.0001423832,0.00123985,0.0001824945,0.00006711118,0.000268499,0.00005889204,0.1015901,0.1661593,0.0076448,0.009548498,0.7127923],"study_design_scores_gemma":[0.00002115077,0.0001338894,0.00067599,0.00001119832,0.00002693612,0.0001765893,0.00001048345,0.9522939,0.04047616,0.001331277,0.004827812,0.00001465197],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05092974,0.000578286,0.9379535,0.0002310665,0.0001581566,0.00008271562,0.0002028955,0.003471535,0.006392055],"genre_scores_gemma":[0.4735852,0.0004198223,0.5163192,0.0002055989,0.00007393228,0.00008558948,0.0006422019,0.00009316931,0.008575251],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00745168,"threshold_uncertainty_score":0.01481664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01843900611008579,"score_gpt":0.2344893313379491,"score_spread":0.2160503252278634,"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."}}