{"id":"W4404024888","doi":"10.1007/978-3-031-73636-0_11","title":"Quantization-Friendly Winograd Transformations for Convolutional Neural Networks","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Quantization (signal processing); Convolutional neural network; Theoretical computer science; Algorithm; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004101088,0.0004082295,0.0003453812,0.0007128451,0.0004158068,0.0006844056,0.001761369,0.0001788998,0.00001282742],"category_scores_gemma":[0.00004329803,0.0003749975,0.0001945644,0.0007171063,0.0004653035,0.001193302,0.0003816922,0.0006063488,0.00002158609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001686534,"about_ca_system_score_gemma":0.0002707878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002670704,"about_ca_topic_score_gemma":0.00001510977,"domain_scores_codex":[0.9971754,0.00001196827,0.0005367334,0.001072279,0.0006136058,0.0005900344],"domain_scores_gemma":[0.9983497,0.0004161296,0.0001491355,0.0006494345,0.0002870289,0.000148559],"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":[0.000003306887,0.00001111276,0.000004485252,0.00003381052,0.000007547201,0.000008772054,0.0002544035,0.2899881,0.00001156762,0.2440872,0.000105546,0.4654842],"study_design_scores_gemma":[0.0001717378,0.00007921943,0.00001109746,0.000165989,0.000007088318,0.0000413652,1.543899e-7,0.8081721,0.00002854396,0.1830955,0.00787819,0.0003490161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000001571408,0.001385097,0.9911729,0.002114328,0.003334472,0.0005127013,0.00001816975,0.0002711209,0.001189639],"genre_scores_gemma":[0.09596326,0.000122161,0.8992295,0.002772806,0.0009735712,0.00004653489,0.00006590294,0.00006824607,0.000757981],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.518184,"threshold_uncertainty_score":0.9998702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01598593845731863,"score_gpt":0.2744193557604303,"score_spread":0.2584334173031116,"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."}}