{"id":"W4385245213","doi":"10.1109/iscas46773.2023.10181694","title":"Training Acceleration of Frequency Domain CNNs Using Activation Compression","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Convolutional neural network; Backpropagation; Overhead (engineering); Training (meteorology); Data compression; Compression (physics); Artificial neural network; Frequency domain; Acceleration; Reduction (mathematics); Time domain; Domain (mathematical analysis); Artificial intelligence; Speech recognition; Computer vision; Operating system","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":[0.0001582021,0.000560226,0.0002104357,0.0003022925,0.000139493,0.0003256525,0.0006678123,0.0003280844,0.004749647],"category_scores_gemma":[0.0008685845,0.0001814569,0.0002123266,0.0003228982,0.0001699904,0.0005820307,0.0003772076,0.0005913058,0.001297162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003436166,"about_ca_system_score_gemma":0.0004994093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004440194,"about_ca_topic_score_gemma":0.007060161,"domain_scores_codex":[0.9998925,0.000008553637,0.000006849602,0.00002313196,0.00004389884,0.00002520108],"domain_scores_gemma":[0.9997776,0.00006720233,0.00001657444,0.0000537653,0.00007382055,0.00001112247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000350735,0.0001863945,0.002797095,0.0001982293,0.00006956073,0.0003179883,0.0001348044,0.1781812,0.1571777,0.004850972,0.009795124,0.6459402],"study_design_scores_gemma":[0.00002105489,0.00008898319,0.001938321,0.00001562787,0.00001707524,0.0001732347,0.00002587993,0.9212674,0.0681996,0.001627597,0.0066132,0.00001197602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3300881,0.0008604825,0.6336601,0.000538788,0.0004313357,0.0001461008,0.0005974658,0.01423749,0.01944004],"genre_scores_gemma":[0.7912488,0.0003454457,0.1972872,0.0001918356,0.00005366017,0.0001176028,0.001048249,0.0003287187,0.009378496],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004749647,"threshold_uncertainty_score":0.01588917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1408461285418412,"score_gpt":0.3460692291120258,"score_spread":0.2052231005701845,"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."}}