{"id":"W4321764792","doi":"10.22541/au.167727732.20256861/v1","title":"HESSPROP: Mitigating Memristive DNN Weight Mapping Errors with Hessian Backpropagation","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"MNIST database; Backpropagation; Hessian matrix; Maxima and minima; Artificial neural network; Gradient descent; Stochastic gradient descent; Robustness (evolution); Computer science; Memristor; Artificial intelligence; Algorithm; Convolutional neural network; Pattern recognition (psychology); Mathematics; Applied mathematics; Electronic engineering; Engineering; Mathematical analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007229001,0.00125938,0.0004566325,0.0004495217,0.0003345716,0.0006450407,0.001275935,0.0009580851,0.002803185],"category_scores_gemma":[0.001663613,0.0003992677,0.0003018329,0.0003076653,0.0005076387,0.0009338453,0.001057712,0.001040842,0.0005515337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005962586,"about_ca_system_score_gemma":0.001091677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003190291,"about_ca_topic_score_gemma":0.005907593,"domain_scores_codex":[0.9997889,0.00003632339,0.00001423107,0.00003512435,0.00009991958,0.00002555748],"domain_scores_gemma":[0.9996217,0.0001302832,0.00003904969,0.00004870503,0.0001397009,0.0000204879],"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":[0.0001091018,0.0001125059,0.0009175052,0.0002241754,0.0001303347,0.0001708657,0.00008563258,0.704373,0.02440435,0.01131734,0.006736032,0.251419],"study_design_scores_gemma":[0.000005180702,0.00002578973,0.00008029338,0.000007139435,0.00000572522,0.00002141803,0.000004868569,0.9914382,0.006220775,0.001430929,0.0007555021,0.000004247325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0298789,0.0004076304,0.9635619,0.000216283,0.0001043095,0.00007433999,0.00007711677,0.002700671,0.002978999],"genre_scores_gemma":[0.5944065,0.0003694493,0.3896413,0.0003088021,0.00007643977,0.0002278601,0.0002691255,0.0006591064,0.01404136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003190291,"threshold_uncertainty_score":0.009377539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03380868750380305,"score_gpt":0.2401455740023423,"score_spread":0.2063368864985393,"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."}}