{"id":"W4211085526","doi":"10.1145/3490422.3502364","title":"FILM-QNN: Efficient FPGA Acceleration of Deep Neural Networks with Intra-Layer, Mixed-Precision Quantization","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Computer science; Field-programmable gate array; Quantization (signal processing); Speedup; Computation; Parallel computing; Stratix; Computer engineering; Edge device; Throughput; Artificial neural network; Hardware acceleration; Algorithm; Embedded system; 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":[0.0003769957,0.0006742387,0.0002889454,0.0003557854,0.0002170027,0.0004558642,0.001130681,0.0002697354,0.004017522],"category_scores_gemma":[0.0007622485,0.0002315756,0.0002546583,0.0003449813,0.0002482644,0.0009129877,0.0004396325,0.0005841742,0.0005203052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008796909,"about_ca_system_score_gemma":0.001083051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01549028,"about_ca_topic_score_gemma":0.02920282,"domain_scores_codex":[0.9998067,0.00002116327,0.00001262796,0.00004487122,0.00008407541,0.00003057601],"domain_scores_gemma":[0.9998098,0.00004863291,0.00001806593,0.00003837839,0.00007071722,0.00001438081],"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":[0.0009650876,0.0002197801,0.003255599,0.0004482612,0.0001358029,0.0003926208,0.0001383501,0.3650721,0.07107297,0.01255393,0.02177618,0.5239693],"study_design_scores_gemma":[0.00007547379,0.0001487051,0.0004948276,0.0000166741,0.00001494024,0.00005454104,0.00001974411,0.9724357,0.0207402,0.0013716,0.004615447,0.00001216271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1483388,0.002106202,0.8150854,0.0004292382,0.000431317,0.0002243736,0.000916574,0.01582048,0.01664772],"genre_scores_gemma":[0.5956595,0.0004211463,0.3954882,0.0002102487,0.00002729935,0.0001083275,0.001091815,0.0002859939,0.006707469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01549028,"threshold_uncertainty_score":0.03080022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01767659962897853,"score_gpt":0.2546906161643103,"score_spread":0.2370140165353318,"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."}}