{"id":"W2757810720","doi":"10.1109/iscas.2017.8050985","title":"A population-level approach to temperature robustness in neuromorphic systems","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Office of Naval Research","keywords":"Robustness (evolution); Neuromorphic engineering; Computer science; Population; Silicon; Decoding methods; Biological system; Artificial neural network; Control theory (sociology); Materials science; Algorithm; Artificial intelligence; Optoelectronics; Chemistry; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006887526,0.0001039977,0.0001424179,0.00005379921,0.0001346434,0.00009922263,0.0001941634,0.00005044137,0.000001836769],"category_scores_gemma":[0.00003551185,0.00009461162,0.0000170764,0.00006863372,0.000005489139,0.0001844429,0.00004031815,0.000160098,0.000005861316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002187724,"about_ca_system_score_gemma":0.000002397345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003140628,"about_ca_topic_score_gemma":0.00001588702,"domain_scores_codex":[0.9994606,0.00001170228,0.0001325394,0.0001535119,0.00007149403,0.0001701496],"domain_scores_gemma":[0.9995939,0.00001541116,0.00001871776,0.00030326,0.00001278699,0.00005597178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002437324,0.000006651164,0.001082689,0.00005231673,0.000001805996,0.000007686879,0.0000283215,0.9938516,0.00410971,0.000476716,0.00007643097,0.000303612],"study_design_scores_gemma":[0.0004116887,0.00001625079,0.1373946,0.0001159569,0.00000375433,0.00005354679,0.00007208272,0.8592695,0.002056881,0.00003231745,0.0001734735,0.0003999631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829905,0.00003311735,0.012028,0.00002965667,0.0004926862,0.0002087454,0.000002430573,0.0001682097,0.004046668],"genre_scores_gemma":[0.9978868,0.000001460493,0.001500676,0.00002457446,0.0001068027,0.00001418324,0.00000445343,0.00001929182,0.0004417349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1363119,"threshold_uncertainty_score":0.385815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08719073282278801,"score_gpt":0.2538004672363522,"score_spread":0.1666097344135642,"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."}}