{"id":"W2942772093","doi":"10.1109/paap.2018.00036","title":"Accelerating Backward Convolution of Convolutional Neural Networks on BWDSP","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto Scarborough","keywords":"Computer science; Convolutional neural network; Field-programmable gate array; Deep learning; Backpropagation; Reconfigurability; Artificial intelligence; Application-specific integrated circuit; Computer architecture; Artificial neural network; Computer engineering; Convolution (computer science); Embedded system; Computer hardware","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000222494,0.0006547368,0.0003346067,0.0004385718,0.0002361732,0.0003987287,0.0008581202,0.0003058229,0.002832546],"category_scores_gemma":[0.0005295998,0.0002220149,0.0003999717,0.0003818657,0.0002457134,0.000723729,0.0005337602,0.0005466398,0.0008033036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006012677,"about_ca_system_score_gemma":0.001137341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007074375,"about_ca_topic_score_gemma":0.008953786,"domain_scores_codex":[0.9997643,0.00001757795,0.00001443019,0.00005060801,0.0001157963,0.00003727482],"domain_scores_gemma":[0.9998488,0.0000342311,0.0000173997,0.00003329444,0.0000548731,0.00001134942],"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":[0.000444645,0.0001595347,0.002903982,0.0002583571,0.00009206226,0.000286384,0.0001184179,0.1340625,0.1759172,0.00898692,0.007947939,0.6688221],"study_design_scores_gemma":[0.00004136158,0.0001418398,0.0009449719,0.00001289351,0.00003156896,0.000175956,0.0000234487,0.8880053,0.101001,0.001929936,0.007675661,0.00001618103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06937227,0.0003976496,0.9174325,0.0001537452,0.00008520605,0.00005217366,0.0001174695,0.007585227,0.004803629],"genre_scores_gemma":[0.4350764,0.0003053997,0.5553472,0.0001932138,0.00003158791,0.00009505694,0.0005897991,0.0003038589,0.008057525],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007074375,"threshold_uncertainty_score":0.0140664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03675775471560357,"score_gpt":0.2808581940109064,"score_spread":0.2441004392953029,"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."}}