{"id":"W4402753747","doi":"10.1109/mwscas60917.2024.10658697","title":"MSPARQ: A RISC-V Vector Processor Array Optimized for Low-Resolution Neural Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Artificial neural network; Reduced instruction set computing; Resolution (logic); Vector processor; Parallel computing; Instruction set; 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":[0.0002308063,0.0005237522,0.0002027802,0.0002904526,0.00015105,0.00040768,0.001184911,0.000189391,0.0066016],"category_scores_gemma":[0.0004515742,0.0002177206,0.0002280809,0.0003265983,0.0001793281,0.0005715706,0.0002729542,0.0004441172,0.001758461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004309669,"about_ca_system_score_gemma":0.0006230474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001518307,"about_ca_topic_score_gemma":0.002603398,"domain_scores_codex":[0.9998133,0.00002513193,0.00001101595,0.00004640623,0.00006909248,0.00003508974],"domain_scores_gemma":[0.9998442,0.00002976561,0.0000217688,0.00002864505,0.00006329633,0.00001227757],"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":[0.001128655,0.0002801522,0.004700501,0.000698204,0.0001882728,0.0003895839,0.0002006523,0.08260997,0.336931,0.02283023,0.05727141,0.4927713],"study_design_scores_gemma":[0.000324496,0.002270009,0.005938669,0.00006896983,0.0001416634,0.0007854672,0.00006869662,0.5835114,0.284537,0.004861469,0.1173909,0.0001013366],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2400807,0.001847722,0.6785495,0.0003031781,0.000300873,0.0003025808,0.001092249,0.04103575,0.03648736],"genre_scores_gemma":[0.6814305,0.0005245187,0.2960597,0.0002479739,0.00005346486,0.0002175702,0.002791683,0.001091663,0.01758296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0066016,"threshold_uncertainty_score":0.02208453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0077018011910289,"score_gpt":0.2199694569414807,"score_spread":0.2122676557504518,"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."}}