{"id":"W3092451347","doi":"10.3389/fnbot.2020.568359","title":"Nengo and Low-Power AI Hardware for Robust, Embedded Neurorobotics.","year":2020,"lang":"en","type":"article","venue":"PubMed","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Neuromorphic engineering; Spiking neural network; Python (programming language); Interfacing; Workflow; Computer architecture; Artificial neural network; Convolutional neural network; Embedded system; Compiler; Computer hardware; Deep learning; Hardware acceleration; 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":[0.0001596054,0.0003614096,0.0001600831,0.0002447027,0.0003069908,0.0004619941,0.000896983,0.0002891438,0.02720175],"category_scores_gemma":[0.0005094726,0.0001643957,0.0001630313,0.0002215767,0.0002247697,0.0007609378,0.0006067077,0.0005169525,0.004558619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003966614,"about_ca_system_score_gemma":0.0005199681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009335184,"about_ca_topic_score_gemma":0.003215269,"domain_scores_codex":[0.9998926,0.000009065633,0.000006501229,0.00002126001,0.00005011928,0.0000204261],"domain_scores_gemma":[0.999867,0.00002307424,0.00001321085,0.00003841955,0.00004101841,0.0000172547],"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":[0.001179318,0.0001871588,0.003811041,0.001045961,0.00008173082,0.0007328809,0.0004533607,0.01538031,0.1971029,0.09528452,0.1868697,0.4978712],"study_design_scores_gemma":[0.0002331841,0.0002765466,0.00387506,0.0001460905,0.0000678849,0.0008110131,0.00009600715,0.191363,0.1678317,0.02158004,0.6136377,0.00008179162],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1001437,0.003163908,0.6011434,0.001958449,0.001876263,0.0004841571,0.00436432,0.0344123,0.2524536],"genre_scores_gemma":[0.4629463,0.0009038871,0.3838918,0.000793037,0.000121906,0.0008290889,0.005158779,0.001514514,0.1438408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02720175,"threshold_uncertainty_score":0.09099889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03137819273900902,"score_gpt":0.2072118761227482,"score_spread":0.1758336833837392,"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."}}