{"id":"W3128763197","doi":"10.1109/a-sscc48613.2020.9336148","title":"CompAcc: Efficient Hardware Realization for Processing Compressed Neural Networks Using Accumulator Arrays","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Taiwan Semiconductor Manufacturing Company","keywords":"Computer science; Convolutional neural network; Artificial neural network; Accumulator (cryptography); Realization (probability); Computation; Field-programmable gate array; Computer hardware; Chip; Parallel computing; Computer engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001911934,0.0008416509,0.0002743001,0.0006413091,0.0003556238,0.0005940684,0.001911952,0.000411798,0.010238],"category_scores_gemma":[0.0006529052,0.0002713509,0.0002171768,0.0006648299,0.0002652356,0.001104197,0.000571087,0.0004858329,0.001934652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006317424,"about_ca_system_score_gemma":0.0008109381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001817257,"about_ca_topic_score_gemma":0.00514307,"domain_scores_codex":[0.9997978,0.00001933584,0.00001575718,0.0000414962,0.00009332843,0.00003242607],"domain_scores_gemma":[0.9996831,0.00006215542,0.00003807171,0.00006632628,0.0001286313,0.00002183578],"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":[0.001057908,0.0003111411,0.003167547,0.0008527194,0.000191074,0.0007642591,0.0001990176,0.03127927,0.4178287,0.0211807,0.06530065,0.4578671],"study_design_scores_gemma":[0.0002149457,0.0009446813,0.002531051,0.00008885752,0.0000984556,0.0009248938,0.00009956915,0.3751737,0.5360439,0.005590277,0.07818988,0.00009965969],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2158323,0.003111491,0.699531,0.001108661,0.0008524221,0.0004706776,0.002171148,0.03795884,0.03896347],"genre_scores_gemma":[0.6645232,0.0004861975,0.3170184,0.0005224471,0.0001578548,0.000452152,0.002357147,0.0005259114,0.01395663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.010238,"threshold_uncertainty_score":0.03424948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07814666081046574,"score_gpt":0.3188172859913296,"score_spread":0.2406706251808639,"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."}}