{"id":"W4385290324","doi":"10.1109/iscas46773.2023.10181445","title":"HESSPROP: Mitigating Memristive DNN Weight Mapping Errors with Hessian Backpropagation","year":2023,"lang":"en","type":"article","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":"Backpropagation; Hessian matrix; Computer science; Artificial intelligence; Artificial neural network; Mathematics; Applied mathematics","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":[0.0006961553,0.001344561,0.0004741229,0.000455506,0.0003643653,0.0006943839,0.001424518,0.001002233,0.00349012],"category_scores_gemma":[0.001676624,0.0004050956,0.0003218315,0.0003207187,0.0005012125,0.0009111468,0.001040709,0.001130749,0.000685835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006420678,"about_ca_system_score_gemma":0.001250047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003993477,"about_ca_topic_score_gemma":0.007887047,"domain_scores_codex":[0.9997924,0.00003335211,0.00001453939,0.0000380612,0.00009433606,0.00002724671],"domain_scores_gemma":[0.9996459,0.0001201472,0.00003817544,0.00004338014,0.0001320541,0.0000203527],"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":[0.0001069508,0.0001070021,0.0009289444,0.0002237337,0.0001253444,0.0001649457,0.00008482389,0.7035382,0.01932906,0.01110964,0.00819338,0.256088],"study_design_scores_gemma":[0.000005168505,0.00002461891,0.0000758684,0.000008437277,0.00000611218,0.00002204311,0.000005505572,0.9919521,0.005518417,0.001404942,0.0009722428,0.00000446388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02708816,0.0004650529,0.9650906,0.0002374694,0.0001228083,0.00008498993,0.00009791167,0.002971375,0.003841691],"genre_scores_gemma":[0.5697289,0.0004367895,0.4111205,0.0003856649,0.00009202962,0.0002746598,0.0003759868,0.0007503914,0.016835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003993477,"threshold_uncertainty_score":0.0116756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01602854403935014,"score_gpt":0.2162758300549623,"score_spread":0.2002472860156122,"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."}}