{"id":"W3161955086","doi":"10.36227/techrxiv.14593686.v1","title":"Accelerating Convolutional Neural Network Using Discrete Orthogonal Transforms","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"Mitacs","keywords":"Computer science; Parallel computing; Python (programming language); Fast Fourier transform; Convolutional neural network; Xeon Phi; Algorithm; Xeon; Benchmark (surveying); Computational science; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009097567,0.0003938195,0.0004967693,0.00008327308,0.0003987751,0.001445338,0.001151854,0.0002762692,0.0001563449],"category_scores_gemma":[0.00004023555,0.0003430813,0.0003874819,0.0003448586,0.00007357363,0.0007038206,0.001419086,0.0009881137,0.00000446129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008810579,"about_ca_system_score_gemma":0.000631731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001015137,"about_ca_topic_score_gemma":0.00002112516,"domain_scores_codex":[0.9969177,0.0003629288,0.0005760415,0.0009166812,0.0005932528,0.0006334487],"domain_scores_gemma":[0.9985845,0.0001826003,0.0001772013,0.0006710726,0.0002312021,0.000153387],"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":[0.00004241325,0.00008473572,0.00128115,0.000252061,0.000290748,0.0005542256,0.001247907,0.8589154,0.006196635,0.05755061,0.000631764,0.07295233],"study_design_scores_gemma":[0.0003013192,0.00001898176,0.001120654,0.0001576022,0.00002708628,0.0001280051,0.00002045374,0.9889092,0.0006879725,0.008007804,0.0001089054,0.000511975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04513239,0.0007164603,0.9481244,0.0003931001,0.002284195,0.0002051577,0.000005331868,0.0002093061,0.002929623],"genre_scores_gemma":[0.2922153,0.00001316132,0.7057258,0.000799507,0.0008490518,0.00001121537,0.00005252183,0.00002259921,0.0003107526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2470829,"threshold_uncertainty_score":0.9999021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07308178091007009,"score_gpt":0.3191280632003119,"score_spread":0.2460462822902418,"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."}}