{"id":"W3196468539","doi":"","title":"Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision.","year":2021,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Convolutional neural network; Robustness (evolution); Classifier (UML); Deep learning; Implementation; Artificial intelligence; Fault tolerance; Floating point; Embedded system; Computer hardware; Real-time computing; Computer engineering; Distributed computing; Algorithm; Software 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003798851,0.0008700051,0.0004777145,0.0006851661,0.0006406833,0.00133526,0.001698409,0.002476396,0.002353477],"category_scores_gemma":[0.02050556,0.0003806405,0.000541156,0.0002519728,0.003575388,0.003411263,0.003035028,0.003617812,0.0004288173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001376898,"about_ca_system_score_gemma":0.001119524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001053457,"about_ca_topic_score_gemma":0.001081693,"domain_scores_codex":[0.9979856,0.0006773721,0.00008443613,0.0002524868,0.000799248,0.0002008561],"domain_scores_gemma":[0.990524,0.005677651,0.0009663154,0.001481524,0.00109767,0.0002528277],"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":[0.0006892115,0.0001630819,0.004187291,0.0003164086,0.00007035054,0.0007485059,0.0003823993,0.6554035,0.0275781,0.2219601,0.005273099,0.08322798],"study_design_scores_gemma":[0.00001735054,0.0001335243,0.0003056253,0.00004107454,0.00001460716,0.0001651761,0.00004697503,0.8920352,0.01782046,0.08797286,0.001434562,0.00001248552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07548168,0.0007094046,0.9120107,0.002627568,0.0001275682,0.00008069392,0.0001037125,0.0008798785,0.00797879],"genre_scores_gemma":[0.9397677,0.0003187222,0.05688891,0.0004340533,0.00009321075,0.00008179057,0.0001186055,0.0001367077,0.002160296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003798851,"threshold_uncertainty_score":0.02009052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1160243625158531,"score_gpt":0.3468425111027822,"score_spread":0.2308181485869291,"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."}}