{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001102982,0.00006739314,0.00008681911,0.00008576967,0.000138454,0.00002764593,0.000291649,0.00003375118,0.00001063522],"category_scores_gemma":[0.00001501067,0.00006245395,0.00002527372,0.001023496,0.00002017343,0.0006608618,0.00009861475,0.00006118694,0.00001116335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002693804,"about_ca_system_score_gemma":0.00002828414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001087366,"about_ca_topic_score_gemma":0.000002764878,"domain_scores_codex":[0.999252,0.00003138175,0.0001974829,0.000208806,0.0001643093,0.0001460408],"domain_scores_gemma":[0.9994096,0.0001055518,0.0001133023,0.0002864178,0.00005224843,0.00003284225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001201096,0.00001326862,0.0001212268,0.000004839188,0.000002975137,6.75035e-7,0.0007421252,0.01253903,0.8105115,0.1477538,0.000135161,0.02817412],"study_design_scores_gemma":[0.000253368,0.0000317733,0.005542344,0.00005087909,0.000002493995,0.000005504066,0.000221082,0.7013994,0.08943869,0.2025636,0.0002962202,0.0001946],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2478019,0.000002641126,0.7500132,0.0003504355,0.00005419622,0.0001243324,5.243265e-7,0.0002280581,0.001424643],"genre_scores_gemma":[0.7240952,0.000003820729,0.2757627,0.00005317591,0.00003640023,0.00001084163,0.000006683063,0.000004848432,0.0000263671],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7210729,"threshold_uncertainty_score":0.2546799,"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."}}