{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009909756,0.0004666313,0.000542862,0.0005670909,0.001092922,0.0004159923,0.001543083,0.0001757434,0.000002150185],"category_scores_gemma":[0.0002181697,0.0004548749,0.0002378738,0.001079685,0.0001098475,0.0001330397,0.0001402443,0.0006257234,0.00002742394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001093058,"about_ca_system_score_gemma":0.0001055192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000101698,"about_ca_topic_score_gemma":0.000007146823,"domain_scores_codex":[0.9964946,0.000261279,0.0006603974,0.001105362,0.0006180292,0.000860351],"domain_scores_gemma":[0.9966905,0.001477488,0.0002664644,0.00120771,0.000122523,0.0002353091],"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":[0.00005210711,0.0000446224,0.00003381314,0.0001028828,0.00007451073,0.00002143135,0.005385284,0.9681422,0.0001372609,0.0003438546,0.000203421,0.02545867],"study_design_scores_gemma":[0.001347094,0.0002234527,0.0002657934,0.0001855342,0.00003832547,0.0000659842,0.001113807,0.9956124,0.0001624004,0.000234747,0.0002878253,0.0004626793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1091908,0.00004377363,0.8840183,0.0007316322,0.003695628,0.0009450254,0.00001440931,0.00128405,0.00007638793],"genre_scores_gemma":[0.9495588,0.000004092537,0.04958816,0.0001481403,0.0003812873,0.0001197997,0.00001305109,0.00007130751,0.0001153918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.840368,"threshold_uncertainty_score":0.9997903,"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."}}