{"id":"W4225885311","doi":"10.23919/date54114.2022.9774635","title":"FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functions","year":2022,"lang":"en","type":"preprint","venue":"2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Fault tolerance; Inference; Redundancy (engineering); Resilience (materials science); Activation function; Deep neural networks; Artificial neural network; Latency (audio); Word error rate; Artificial intelligence; Distributed computing","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":[0.001247608,0.001938951,0.0007600518,0.0005163904,0.0003399392,0.0008417231,0.002463255,0.001375129,0.002500747],"category_scores_gemma":[0.004052403,0.0005375486,0.0006610281,0.0003129555,0.001032116,0.001933799,0.002181638,0.002518506,0.0009297051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008812991,"about_ca_system_score_gemma":0.001045043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003237545,"about_ca_topic_score_gemma":0.004813911,"domain_scores_codex":[0.9994385,0.00009249536,0.00003052,0.0001374604,0.0002216691,0.00007938998],"domain_scores_gemma":[0.9990999,0.0003343695,0.0001262188,0.0002141186,0.0001695163,0.00005600487],"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":[0.0002213361,0.00009669513,0.0006775365,0.00009870491,0.00008782539,0.0001243679,0.00005194429,0.8713347,0.01135817,0.005160402,0.003302876,0.1074853],"study_design_scores_gemma":[0.000009568693,0.00005479634,0.0000767386,0.000007856489,0.000009243841,0.00002470545,0.000004075997,0.9928765,0.004124498,0.002227463,0.000578205,0.000006369572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0326251,0.0007992922,0.9571821,0.000308058,0.0001426463,0.00007258546,0.0001478935,0.006540668,0.002181667],"genre_scores_gemma":[0.785164,0.0004413396,0.2057365,0.0006556978,0.00009235799,0.0001842983,0.0005879767,0.0005828944,0.00655493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003237545,"threshold_uncertainty_score":0.00836581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04523905429616132,"score_gpt":0.2870918710591243,"score_spread":0.241852816762963,"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."}}