{"id":"W3138783654","doi":"10.1088/2634-4386/abf150","title":"Comparing Loihi with a SpiNNaker 2 prototype on low-latency keyword spotting and adaptive robotic control","year":2021,"lang":"en","type":"article","venue":"Neuromorphic Computing and Engineering","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Research Council Canada; Seventh Framework Programme; Horizon 2020 Framework Programme; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Canada Research Chairs; Natural Sciences and Engineering Research Council of Canada; European Commission; Intel Corporation","keywords":"Neuromorphic engineering; Keyword spotting; Computer science; Benchmark (surveying); Latency (audio); Spiking neural network; Artificial neural network; Spotting; Multiplication (music); Computer architecture; Embedded system; Artificial intelligence; Telecommunications","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":[0.0002997792,0.0005216018,0.0004009681,0.0003035473,0.0002310822,0.0007025637,0.002045262,0.0005262372,0.008995965],"category_scores_gemma":[0.0008889146,0.0001306695,0.000174847,0.0002715929,0.0002997389,0.000967379,0.0004281383,0.0004856842,0.001126064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005854068,"about_ca_system_score_gemma":0.0005685236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001794859,"about_ca_topic_score_gemma":0.002261558,"domain_scores_codex":[0.9997126,0.00003135097,0.00001792714,0.00006131324,0.0001025164,0.0000742698],"domain_scores_gemma":[0.9995135,0.0001141901,0.00004134151,0.000105809,0.0001546918,0.00007050304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003927473,0.001189663,0.00384422,0.002063108,0.0003087073,0.001188403,0.0003923151,0.2136411,0.391861,0.009887149,0.02095806,0.3507389],"study_design_scores_gemma":[0.0002843877,0.003371434,0.003992863,0.00006616469,0.000094625,0.0003401476,0.0002130352,0.5865078,0.3883731,0.001543232,0.01512626,0.00008689939],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.870935,0.0008229022,0.0862455,0.0005499469,0.0004926012,0.0002947748,0.0005461393,0.01286929,0.02724382],"genre_scores_gemma":[0.9718904,0.0001042704,0.02179464,0.0001316439,0.00001323101,0.00008240982,0.0002668955,0.0001554973,0.005561027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008995965,"threshold_uncertainty_score":0.03009456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01776365239032413,"score_gpt":0.1943500965064021,"score_spread":0.1765864441160779,"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."}}