{"id":"W4391094314","doi":"10.1109/paap60200.2023.10391619","title":"A Cost-Effective FPGA-Based Approximate Multiplier for Machine Learning Acceleration","year":2023,"lang":"en","type":"article","venue":"","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada; Institut National de la Recherche Scientifique","funders":"Mitacs","keywords":"Computer science; Multiplier (economics); Field-programmable gate array; Adder; Computer engineering; Inference; Lookup table; Benchmark (surveying); Deep learning; Artificial intelligence; Computation; Computer architecture; Machine learning; Algorithm; Computer hardware","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002523197,0.0006268659,0.0002972732,0.000569761,0.0003187073,0.0006772591,0.001302077,0.0003407359,0.009254883],"category_scores_gemma":[0.001079532,0.0002531272,0.0002154835,0.0005697349,0.0001830942,0.0009995974,0.0004966687,0.0005363296,0.001983755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004138263,"about_ca_system_score_gemma":0.0007619457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008596096,"about_ca_topic_score_gemma":0.002364825,"domain_scores_codex":[0.9998,0.00002851485,0.0000147168,0.00003505429,0.00009272545,0.00002900635],"domain_scores_gemma":[0.9997295,0.00007782751,0.00003328602,0.00005983209,0.0000837192,0.00001596913],"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":[0.0008580252,0.0001366107,0.001897679,0.0004223557,0.00009082521,0.0003955925,0.00007728065,0.07546259,0.1270763,0.03305413,0.01589456,0.744634],"study_design_scores_gemma":[0.0001314833,0.001156424,0.001278327,0.0001039204,0.00008296197,0.001157438,0.00005977612,0.8119814,0.1168199,0.0113073,0.05586952,0.00005147886],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05266763,0.00161793,0.9269457,0.0003464662,0.0003083548,0.000144429,0.0003418396,0.00428183,0.01334583],"genre_scores_gemma":[0.4651462,0.0005401336,0.5239772,0.0002527031,0.00009106438,0.0001359034,0.0004855149,0.0001213469,0.009250038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009254883,"threshold_uncertainty_score":0.03096062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03146114378590124,"score_gpt":0.2626050166354391,"score_spread":0.2311438728495379,"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."}}