{"id":"W2097566223","doi":"10.1109/tcsii.2010.2092827","title":"Current-Mode Analog Adaptive Mechanism for Ultra-Low-Power Neural Networks","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits & Systems II Express Briefs","topic":"Analog and Mixed-Signal Circuit Design","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"CMOS; Capacitor; Computer science; Chip; Artificial neural network; Transistor; Electrical engineering; Low-power electronics; Electronic engineering; Leakage (economics); Realization (probability); Wireless; Embedded system; Power (physics); Engineering; Artificial intelligence; Telecommunications; Power consumption; Voltage; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002412913,0.000615146,0.0006783092,0.0002950621,0.0005120965,0.00007950864,0.0004759594,0.0003535979,0.00007683077],"category_scores_gemma":[0.000005782712,0.0006520037,0.0004218353,0.0003366148,0.00008413765,0.0004306117,0.000001438834,0.0006582754,0.00003693541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001704314,"about_ca_system_score_gemma":0.00005054623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002149631,"about_ca_topic_score_gemma":0.00004042293,"domain_scores_codex":[0.9971464,0.0001404584,0.0007355158,0.000673596,0.0003805006,0.0009234902],"domain_scores_gemma":[0.9984747,0.0001781469,0.0001335164,0.0006179532,0.0002415238,0.0003541276],"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":[0.0001724456,0.0008083989,0.000008759403,0.0006055968,0.001104208,0.0000549884,0.006662614,0.8373756,0.04102322,0.08519163,0.004087854,0.0229047],"study_design_scores_gemma":[0.007969423,0.003006444,0.0001065152,0.002538907,0.001498904,0.0004448469,0.002721668,0.8205436,0.1429239,0.007387047,0.004299576,0.006559153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0037498,0.0008847184,0.9848199,0.000001629773,0.005849571,0.00129321,0.0003835082,0.0008647282,0.002152878],"genre_scores_gemma":[0.9982305,0.00008993169,0.0000278475,0.00005732599,0.0002976869,0.0008946382,0.00001497319,0.0001803719,0.0002066838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9944807,"threshold_uncertainty_score":0.9995931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02977068939401622,"score_gpt":0.2257262805046497,"score_spread":0.1959555911106335,"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."}}