{"id":"W2615084988","doi":"10.1145/3060403.3060435","title":"Evaluating Data Resilience in CNNs from an Approximate Memory Perspective","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Resilience (materials science); Error detection and correction; Computer engineering; Implementation; Volume (thermodynamics); Memory management; Parallel computing; Algorithm; Semiconductor memory; Artificial intelligence; Computer hardware","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003974717,0.0001036847,0.0001159699,0.00003708062,0.0004261416,0.0002765219,0.005389045,0.00003067848,0.00001659225],"category_scores_gemma":[0.0002897356,0.00009571563,0.00001204916,0.0001320422,0.000101044,0.00280221,0.001505489,0.0001507488,0.00003867567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005908183,"about_ca_system_score_gemma":0.00005568897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00103235,"about_ca_topic_score_gemma":0.001095075,"domain_scores_codex":[0.9983729,0.00006602603,0.0001665803,0.0009173545,0.000237897,0.0002392302],"domain_scores_gemma":[0.9945176,0.0001351768,0.0001479891,0.005053815,0.00006789511,0.00007751826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003386623,0.0004416306,0.005799896,0.000007419053,0.00002138929,0.00005353154,0.008265641,0.01978188,0.02296893,0.4401874,0.000913361,0.5015251],"study_design_scores_gemma":[0.0001915513,0.00002331624,0.01947103,0.000009404411,0.000002011866,0.000001901221,0.0003551464,0.9242212,0.0009485553,0.05460292,0.00003445453,0.000138471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09942027,0.00007980784,0.8776397,0.003956348,0.0001512047,0.0004480337,0.00001768988,0.000238661,0.01804825],"genre_scores_gemma":[0.6510746,0.000006559885,0.3484378,0.0001882239,0.00007349506,0.00002622303,0.000008242376,0.00000640084,0.0001784728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9044393,"threshold_uncertainty_score":0.9999923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1583669576298885,"score_gpt":0.4426131248123565,"score_spread":0.284246167182468,"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."}}