{"id":"W4416559751","doi":"10.1016/j.array.2025.100594","title":"A real-valued DCT-based spectral CNN architecture for efficient edge deep learning","year":2025,"lang":"en","type":"article","venue":"Array","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto Mississauga; Universiti Teknologi Malaysia","keywords":"MNIST database; Convolutional neural network; Discrete cosine transform; Reduction (mathematics); Benchmark (surveying); Convolution (computer science); Throughput; Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0001282344,0.0001377334,0.0001407355,0.0001010774,0.0002956948,0.00005767131,0.000596143,0.00004570258,0.000004426168],"category_scores_gemma":[0.00006017138,0.0001280945,0.00009580763,0.0006139751,0.00004677762,0.00004369863,0.00006370162,0.0002068018,0.00002312257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006133891,"about_ca_system_score_gemma":0.00006039078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005108738,"about_ca_topic_score_gemma":0.00001376328,"domain_scores_codex":[0.998849,0.00004823634,0.0001725052,0.0004513006,0.0001246303,0.0003543582],"domain_scores_gemma":[0.9990107,0.0002931205,0.00007032569,0.0005065779,0.00005070325,0.00006850823],"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":[0.00003330112,0.00009742057,0.000132044,0.00003123581,0.00001951651,0.000002709249,0.0004594724,0.7808409,0.03656239,0.1217179,0.0008900966,0.05921302],"study_design_scores_gemma":[0.0008557681,0.0001252002,0.001054633,0.00004242162,0.00001725657,0.000003011133,0.00001977052,0.9151891,0.02687793,0.01482494,0.04068873,0.0003012517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01039676,0.00006498495,0.9831537,0.002512682,0.0002038339,0.000478898,0.000001254769,0.000341024,0.002846857],"genre_scores_gemma":[0.603365,0.000003983333,0.3948042,0.0007033878,0.0001079265,0.000216149,0.000009144461,0.00001433213,0.0007758553],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5929683,"threshold_uncertainty_score":0.5223542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01078823703893809,"score_gpt":0.2715870794746342,"score_spread":0.2607988424356961,"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."}}