{"id":"W4401273062","doi":"10.32604/cmc.2024.053632","title":"A Novel Quantization and Model Compression Approach for Hardware Accelerators in Edge Computing","year":2024,"lang":"en","type":"article","venue":"Computers, materials & continua/Computers, materials & continua (Print)","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chongqing University of Science and Technology; Chongqing Municipal Education Commission; Chongqing University; Chinese Academy of Sciences","keywords":"Computer science; Quantization (signal processing); Enhanced Data Rates for GSM Evolution; Hardware acceleration; Data compression; Computer hardware; Computer architecture; Computational science; Parallel computing; Field-programmable gate array; Artificial intelligence; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.003326562,0.001586162,0.00262203,0.0009694505,0.0005637845,0.007568792,0.00304309,0.000690542,0.00002702863],"category_scores_gemma":[0.0001266887,0.001582435,0.0003580475,0.0009506837,0.000247326,0.001841582,0.002800964,0.0004567604,0.000062107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000294268,"about_ca_system_score_gemma":0.0003078469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002967748,"about_ca_topic_score_gemma":0.00001099485,"domain_scores_codex":[0.9901508,0.0007484155,0.003069654,0.003270322,0.0008204335,0.001940358],"domain_scores_gemma":[0.9955484,0.0008518687,0.001016182,0.00161264,0.0005226137,0.0004482497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006100008,0.001191866,0.0005468661,0.006462114,0.000741363,0.0002546349,0.01039721,0.03225999,0.8109865,0.07321796,0.0294117,0.03391976],"study_design_scores_gemma":[0.004568157,0.0003025394,0.001794319,0.003877561,0.0001078625,0.0003561153,0.0001071114,0.94124,0.03653805,0.001004759,0.007587808,0.002515682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.265406,0.0005636645,0.7201911,0.000290012,0.009077893,0.002458624,0.0003761671,0.00147797,0.0001586782],"genre_scores_gemma":[0.8106895,0.0000448655,0.1860713,0.00038728,0.001582315,0.0001721632,0.0007074074,0.0001810891,0.0001640158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9089801,"threshold_uncertainty_score":0.9996886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0287741636614898,"score_gpt":0.2644025147763159,"score_spread":0.2356283511148261,"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."}}