{"id":"W2787094505","doi":"10.1109/fpt.2017.8280142","title":"An FPGA-based processor for training convolutional neural networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Field-programmable gate array; Scalability; Convolutional neural network; Computation; Process (computing); Parallel computing; Speedup; Computer architecture; Embedded system; Artificial intelligence; Operating system; Programming language","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":[0.0001179227,0.000433855,0.0002021865,0.0003403339,0.0001882707,0.0002920434,0.0006421935,0.0002130092,0.00777598],"category_scores_gemma":[0.0002762495,0.0001451368,0.0001676425,0.0004033737,0.00009200029,0.0004048568,0.0001905143,0.0003455268,0.001526679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003293979,"about_ca_system_score_gemma":0.0005605812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001200828,"about_ca_topic_score_gemma":0.001917079,"domain_scores_codex":[0.9998939,0.00001354939,0.000007702841,0.00002506573,0.00003619358,0.00002353945],"domain_scores_gemma":[0.9999087,0.00002015875,0.000009386889,0.00001788376,0.00003547886,0.000008359398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001087329,0.0002581826,0.004051137,0.0006053551,0.0001363271,0.0007294674,0.00009818169,0.05045826,0.212508,0.01416355,0.03719939,0.6787047],"study_design_scores_gemma":[0.0004382748,0.001856276,0.00629781,0.00012524,0.0001821542,0.001540895,0.0000827135,0.6442823,0.2404262,0.003380602,0.1013178,0.00006973477],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2089211,0.001675215,0.7357975,0.0003961681,0.0005900016,0.0003729197,0.0007817131,0.01544231,0.03602308],"genre_scores_gemma":[0.6957859,0.0005766262,0.2867476,0.0003215532,0.00007669638,0.0002192315,0.001141397,0.0001596942,0.01497131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00777598,"threshold_uncertainty_score":0.02601331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06517504108062533,"score_gpt":0.3329627680702296,"score_spread":0.2677877269896043,"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."}}