{"id":"W2165433905","doi":"10.1109/icnn.1994.374520","title":"Analog hardware tolerance of soft competitive learning","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"CMC Microsystems","keywords":"CMOS; Computer science; Competitive learning; Noise (video); Transistor; Artificial neural network; Artificial intelligence; Electronic engineering; Computer 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":[0.00002114979,0.00006552523,0.0001068285,0.00002357792,0.00003452247,0.000003521425,0.00005133212,0.00001926026,0.0003187203],"category_scores_gemma":[0.00001578244,0.00006412333,0.00002941423,0.00008947217,0.00001232501,0.00006990408,0.00001270454,0.0001271801,0.00003537055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007725077,"about_ca_system_score_gemma":5.57489e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.596222e-7,"about_ca_topic_score_gemma":0.000001472657,"domain_scores_codex":[0.9996479,0.000008579871,0.0001035269,0.00007343349,0.00005149716,0.000115078],"domain_scores_gemma":[0.9998276,0.00005372675,0.00001580657,0.00005893569,0.00001898375,0.00002499111],"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":[0.000002739229,0.00001031491,0.0008824848,0.00006952248,0.00001309215,0.00001094379,0.0004834543,0.9568685,0.02203767,0.001852187,0.0002361931,0.01753293],"study_design_scores_gemma":[0.0003773861,0.00008054683,0.001882435,0.00011706,0.000007842706,0.0000152537,0.0003035724,0.8299125,0.1538251,0.0001728203,0.01299345,0.0003119861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7646008,0.0009038344,0.08973367,0.00003169176,0.0002551052,0.00009446341,0.000002464423,0.0007249264,0.1436531],"genre_scores_gemma":[0.9979564,0.00002429611,0.0009994026,0.00002645232,0.00003928128,8.417516e-7,8.777113e-7,0.000009864497,0.0009425991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2333556,"threshold_uncertainty_score":0.3489763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01594452411916895,"score_gpt":0.2072283536320191,"score_spread":0.1912838295128502,"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."}}