{"id":"W3197843460","doi":"10.1109/itw48936.2021.9611431","title":"Power-Efficient Deep Neural Networks with Noisy Memristor Implementation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Agence Nationale de la Recherche","keywords":"Memristor; Computation; Artificial neural network; Karush–Kuhn–Tucker conditions; Computer science; Nonlinear system; Covariance; Inference; Power (physics); Algorithm; Artificial intelligence; Control theory (sociology); Mathematics; Mathematical optimization; Electronic engineering; Statistics; 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":[0.00006928592,0.0003126498,0.0002748267,0.00005705029,0.00008070804,0.0000818116,0.0001599745,0.0001152988,0.0002723919],"category_scores_gemma":[0.000003617765,0.000282761,0.00008806394,0.0001266386,0.00001703978,0.00005483659,0.0002248047,0.0006221676,0.000002859053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001265449,"about_ca_system_score_gemma":0.00001411748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007571092,"about_ca_topic_score_gemma":0.00006383174,"domain_scores_codex":[0.9987876,0.00002787229,0.0002847149,0.0003785427,0.0001730521,0.0003481843],"domain_scores_gemma":[0.9994143,0.00004199371,0.00006779245,0.0003280558,0.00005709925,0.00009077727],"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":[0.000007523082,0.000008402945,0.00004756527,0.00005876565,0.00003520429,0.00004117254,0.0002189513,0.9934352,0.0004031303,0.00002164381,0.00004866307,0.005673781],"study_design_scores_gemma":[0.0002472241,0.00003807469,0.0003772563,0.00004284716,0.00002736081,0.00002346407,0.0005577448,0.9934571,0.004667643,0.000006334758,0.0001421937,0.0004127401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4927287,0.0005023933,0.5038654,0.00002146878,0.001066965,0.0002441369,0.000002184184,0.00044415,0.001124625],"genre_scores_gemma":[0.9948581,0.00001672376,0.004639535,0.00008976944,0.0001800947,0.00002734116,0.00009609446,0.00006032307,0.00003201617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5021294,"threshold_uncertainty_score":0.9999624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009865408630291601,"score_gpt":0.2483759641836343,"score_spread":0.2385105555533427,"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."}}