{"id":"W2115861312","doi":"10.1109/iscas.1993.394263","title":"Analog neural network building blocks based on current mode subthreshold operation","year":2002,"lang":"en","type":"article","venue":"1993 IEEE International Symposium on Circuits and Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Subthreshold conduction; Artificial neural network; Comparator; Computer science; Electronic engineering; Current (fluid); Analog signal; Analog signal processing; Amplifier; Operational amplifier; Electronic circuit; Multiplier (economics); Field-programmable analog array; Analogue electronics; Feed forward; Electrical engineering; Analog multiplier; Transistor; Artificial intelligence; CMOS; Voltage; Engineering; Computer hardware; Control engineering; Digital signal processing","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":[0.0002032657,0.0002199705,0.0001983835,0.00009543155,0.0002916404,0.000576959,0.0006205057,0.00006772731,0.00001584621],"category_scores_gemma":[0.000005235634,0.0001915802,0.00007899351,0.000211337,0.00002765528,0.0002645368,0.00004239731,0.0002283651,0.00002712787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008533799,"about_ca_system_score_gemma":0.000009400583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005133997,"about_ca_topic_score_gemma":0.000006923736,"domain_scores_codex":[0.9981244,0.00006989938,0.0003882246,0.000578307,0.0005346814,0.0003045248],"domain_scores_gemma":[0.9990761,0.0001471977,0.0001540878,0.0003867958,0.00009607388,0.0001397895],"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":[0.000003978772,0.0001415418,0.0007703691,0.00001037886,0.0000152642,0.000007685589,0.00005718823,0.9197093,0.002419223,0.05828124,0.00868474,0.009899057],"study_design_scores_gemma":[0.0003136206,0.00009882227,0.0002819679,0.0001119132,0.000005452079,0.00001506617,0.00000177932,0.9869274,0.0001480105,0.0001279424,0.01175595,0.0002120973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4063556,0.001641572,0.5258766,0.01731671,0.02472102,0.002195942,0.0001325847,0.0007492424,0.0210106],"genre_scores_gemma":[0.9973976,0.00008825021,0.00006124539,0.0007028867,0.001361116,0.00009708416,0.00001518457,0.00001490844,0.0002617216],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5910419,"threshold_uncertainty_score":0.7812415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0419612648578287,"score_gpt":0.2799327835935417,"score_spread":0.237971518735713,"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."}}