{"id":"W4416183714","doi":"10.1109/mipr67560.2025.00030","title":"Neural Network Structural Pruning and Acceleration in Frequency Domain","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Frequency domain; Inference; Acceleration; Discrete cosine transform; Computation; Artificial neural network; Set (abstract data type); Discrete Fourier transform (general); Domain (mathematical analysis)","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"],"consensus_categories":[],"category_scores_codex":[0.0002511358,0.0003296948,0.0003195761,0.000179932,0.0005601937,0.0004558795,0.000721397,0.0001455413,0.00003960055],"category_scores_gemma":[0.00002822949,0.0003339923,0.00004826513,0.002357329,0.0001651048,0.001320824,0.0006390453,0.0005009748,0.000006040801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000124177,"about_ca_system_score_gemma":0.0001078082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007712445,"about_ca_topic_score_gemma":0.0005483981,"domain_scores_codex":[0.9972994,0.0001827735,0.0006830184,0.0009291435,0.0001954715,0.0007102346],"domain_scores_gemma":[0.9987202,0.0002550493,0.0001636254,0.0006672056,0.00007647429,0.0001174651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001064916,0.00001462014,0.02120921,0.00002181833,0.00001060942,0.000009160052,0.0003813336,0.02550904,0.0007336637,0.8659568,0.0003226494,0.08582042],"study_design_scores_gemma":[0.000456793,0.00003820326,0.06794165,0.00007219761,0.0000067736,0.00001192332,0.000041461,0.513778,0.00005002565,0.4171107,0.0002197111,0.0002725295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3965829,0.002543885,0.5794527,0.007751141,0.001051297,0.001141219,0.000001670328,0.000171728,0.0113035],"genre_scores_gemma":[0.8053409,0.0001143877,0.192774,0.001174964,0.0001774969,0.00005351546,0.000004185227,0.0000102984,0.0003503253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.488269,"threshold_uncertainty_score":0.9999112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01594840621238933,"score_gpt":0.2816929085465006,"score_spread":0.2657445023341113,"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."}}