{"id":"W4366087622","doi":"10.1145/3593045","title":"<i>XploreNAS</i> : Explore Adversarially Robust and Hardware-efficient Neural Architectures for Non-ideal Xbars","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Embedded Computing Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Robustness (evolution); Crossbar switch; Benchmark (surveying); Software deployment; Artificial neural network; Deep neural networks; Ideal (ethics); Computer engineering; Hardware acceleration; Distributed computing; Embedded system; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004780805,0.0009098536,0.0002688899,0.0002827583,0.0002532242,0.0006338647,0.001153852,0.0006115417,0.006100233],"category_scores_gemma":[0.0009989071,0.0002452605,0.0003600602,0.0001648441,0.0004835256,0.0008974924,0.0009110733,0.001026758,0.001290888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005362749,"about_ca_system_score_gemma":0.0005971219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001582154,"about_ca_topic_score_gemma":0.003678222,"domain_scores_codex":[0.9998891,0.00002281358,0.000004925819,0.00002124587,0.00003920699,0.00002268694],"domain_scores_gemma":[0.9997721,0.00008402136,0.0000271017,0.00005412347,0.00004297448,0.00001962119],"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":[0.0002245237,0.0001266248,0.002033609,0.0002095199,0.0001265061,0.0002049871,0.00006881529,0.754261,0.03938764,0.02018765,0.02128914,0.1618799],"study_design_scores_gemma":[0.00001654085,0.0001115442,0.0001511569,0.00001546533,0.00001045216,0.00003879717,0.00001465153,0.978066,0.01322575,0.003760378,0.004581727,0.000007560051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1347101,0.001163354,0.8182919,0.001714433,0.0003440462,0.0002397355,0.0003761201,0.01243555,0.03072477],"genre_scores_gemma":[0.6331028,0.0004953708,0.351661,0.0008264566,0.00006630147,0.0002935203,0.0007358555,0.000925002,0.0118937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006100233,"threshold_uncertainty_score":0.02040732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03607965429794133,"score_gpt":0.281352260344326,"score_spread":0.2452726060463847,"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."}}