{"id":"W3045034882","doi":"10.3389/fnbot.2020.568359","title":"Nengo and Low-Power AI Hardware for Robust, Embedded Neurorobotics","year":2020,"lang":"en","type":"preprint","venue":"Frontiers in Neurorobotics","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Neuromorphic engineering; Computer science; Spiking neural network; Python (programming language); Interfacing; Workflow; Computer architecture; Artificial neural network; Embedded system; Compiler; Hardware acceleration; Computer hardware; Convolutional neural network; Artificial intelligence; Field-programmable gate array; Operating system","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":[0.0004518935,0.0006992149,0.0002655073,0.0002928665,0.0003500199,0.0009366049,0.002162304,0.000499561,0.02587231],"category_scores_gemma":[0.00174343,0.0004654706,0.0006206367,0.0002122659,0.0006454226,0.001675472,0.001406322,0.001363349,0.005142867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007825815,"about_ca_system_score_gemma":0.0009314545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002008857,"about_ca_topic_score_gemma":0.002858802,"domain_scores_codex":[0.999726,0.00002734775,0.00001526672,0.00004908653,0.0001409783,0.00004126831],"domain_scores_gemma":[0.9995632,0.0001282309,0.00003717025,0.0001429881,0.00008822122,0.00004026439],"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":[0.001148699,0.000269837,0.00695674,0.001735813,0.0002553774,0.0009795438,0.0009475969,0.1553518,0.1240634,0.2155783,0.1356296,0.3570833],"study_design_scores_gemma":[0.0001403798,0.0001955557,0.002450191,0.0002352366,0.00008258361,0.0005542866,0.00007351452,0.4590513,0.09590807,0.04817988,0.3929994,0.0001295702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02469619,0.0006409831,0.8148184,0.0008388134,0.0004394527,0.0001584707,0.001446374,0.07560548,0.08135585],"genre_scores_gemma":[0.3791214,0.0007230331,0.5631357,0.001242829,0.00009580648,0.0006472302,0.003416847,0.01105973,0.04055743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02587231,"threshold_uncertainty_score":0.08655155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02455480800232665,"score_gpt":0.2430092921898781,"score_spread":0.2184544841875515,"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."}}