{"id":"W4319078291","doi":"10.22541/au.167543651.10481778/v1","title":"A Survey of Ensemble Methods for Mitigating Memristive Neural Network Non-idealities","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"MNIST database; Weighting; Artificial neural network; Computer science; Voting; Ensemble learning; Ensemble forecasting; Work (physics); Ensemble average; Artificial intelligence; Machine learning; Algorithm; Data mining; Pattern recognition (psychology); Engineering","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":[0.001378193,0.0003350807,0.0007088119,0.00007014523,0.00008992539,0.00002789286,0.0002584157,0.0001993045,0.000005991591],"category_scores_gemma":[0.0005154724,0.0003426555,0.0001912478,0.0002025836,0.00004043943,0.00004845072,0.0003927214,0.0005121561,0.000001882192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004172148,"about_ca_system_score_gemma":0.00003178057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002144959,"about_ca_topic_score_gemma":0.000135041,"domain_scores_codex":[0.9982786,0.0001895247,0.0006097757,0.0003654429,0.00009613814,0.0004605189],"domain_scores_gemma":[0.9955449,0.003726217,0.0001709176,0.0003190499,0.0001692762,0.00006961928],"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":[0.00001647642,0.000002554848,0.0001813419,0.0009292475,0.00009627415,0.000001672453,0.000218692,0.981203,0.00177289,0.00009243617,0.0008938871,0.01459153],"study_design_scores_gemma":[0.0001762871,0.00004029552,0.00326505,0.000365733,0.00003815576,0.000001521124,0.0001182515,0.9485661,0.03876476,0.008163198,0.00005991277,0.0004407472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07453218,0.0005561959,0.920171,0.00001511292,0.002490808,0.0006392829,0.00009761949,0.00066339,0.0008344089],"genre_scores_gemma":[0.677582,0.00004656965,0.3208317,0.00003320221,0.0004482487,0.0001166389,0.000187409,0.0001408902,0.0006132828],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6030498,"threshold_uncertainty_score":0.9999025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1111162934476659,"score_gpt":0.3793379323547438,"score_spread":0.268221638907078,"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."}}