{"id":"W4243049722","doi":"10.36227/techrxiv.14593686","title":"Accelerating Convolutional Neural Network Using Discrete Orthogonal Transforms","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Computer science; Parallel computing; Python (programming language); Convolutional neural network; Fast Fourier transform; Xeon Phi; Algorithm; Xeon; Benchmark (surveying); CUDA; Artificial neural network; Computational science; Artificial intelligence; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006563312,0.0009780867,0.0005936705,0.0006408404,0.0002727378,0.0007380138,0.001272724,0.000771702,0.006375622],"category_scores_gemma":[0.002682289,0.0003450806,0.0006649265,0.0008419557,0.0003725121,0.001223029,0.001122838,0.001487002,0.002763155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001299871,"about_ca_system_score_gemma":0.001424311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02167876,"about_ca_topic_score_gemma":0.0300185,"domain_scores_codex":[0.9996285,0.00003899399,0.00001627348,0.00008770845,0.000165404,0.00006299901],"domain_scores_gemma":[0.9994759,0.0001803985,0.0000316451,0.0001189557,0.0001599642,0.00003307344],"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":[0.0001851431,0.0001097944,0.001351106,0.0001739699,0.0001280478,0.0001476766,0.00008082564,0.7644469,0.009586605,0.009745878,0.02050259,0.1935414],"study_design_scores_gemma":[0.000007653445,0.00000943458,0.0001291616,0.000003329574,0.00000384681,0.00001047564,0.000004595553,0.996243,0.001630365,0.0009303932,0.001024753,0.000002981547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1040879,0.001223057,0.8417153,0.0006035156,0.0004661415,0.0001222242,0.001135905,0.0329661,0.01767981],"genre_scores_gemma":[0.5048357,0.0005498195,0.470626,0.0003362026,0.0000840535,0.0002112158,0.004206236,0.001810538,0.01734032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02167876,"threshold_uncertainty_score":0.04310519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05815903960112196,"score_gpt":0.2910011506619982,"score_spread":0.2328421110608762,"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."}}