{"id":"W3131200591","doi":"10.1109/jstqe.2022.3218019","title":"Dynamic Precision Analog Computing for Neural Networks","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Quantum Electronics","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Noise (video); Artificial neural network; Analog computer; Computer engineering; Artificial intelligence; Effective number of bits; Electronic engineering; Electrical engineering; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001185628,0.0002060324,0.0004180747,0.0003360559,0.0004333768,0.0001297219,0.001554912,0.00008208011,0.000002684531],"category_scores_gemma":[0.0001003678,0.0001928784,0.0001843618,0.001613606,0.00002129177,0.0002595392,0.0002657218,0.001558799,1.346128e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004391987,"about_ca_system_score_gemma":0.000277959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004296995,"about_ca_topic_score_gemma":0.00002603439,"domain_scores_codex":[0.9971981,0.0002993035,0.0008916527,0.0003237936,0.0004911126,0.0007960372],"domain_scores_gemma":[0.9980321,0.0004778734,0.0006769676,0.0002855194,0.0004309917,0.00009652996],"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":[0.00006974001,0.0001028038,0.0004896868,0.00001048811,0.000030143,0.00005375075,0.0001122481,0.9583355,0.0004411195,0.002604116,0.00052784,0.03722262],"study_design_scores_gemma":[0.000786834,0.001316843,0.0007764829,0.00002762529,0.0000106998,0.0004317081,0.00001422753,0.9895357,0.00008920199,0.005187031,0.001619099,0.0002045056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5077177,0.002775331,0.4867098,0.0008734182,0.001692237,0.0001903116,6.190123e-7,0.00003349378,0.000007075314],"genre_scores_gemma":[0.9906093,0.0001911998,0.008458047,0.0002802739,0.0004013074,0.000004381709,0.000002851356,0.00002232503,0.00003035116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4828916,"threshold_uncertainty_score":0.7865353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01191848047118777,"score_gpt":0.2628128037727684,"score_spread":0.2508943233015806,"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."}}