{"id":"W3089057106","doi":"10.1109/tcsii.2020.3026642","title":"AIDX: Adaptive Inference Scheme to Mitigate State-Drift in Memristive VMM Accelerators","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits & Systems II Express Briefs","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut interdisciplinaire d'innovation technologique; Université de Sherbrooke; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Computer science; Memristor; Convolutional neural network; Artificial neural network; Artificial intelligence; Scheme (mathematics); Pattern recognition (psychology); Algorithm; Electronic engineering; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001059098,0.0004159373,0.0005176249,0.000192026,0.0002391931,0.00007503433,0.0003264893,0.0001277774,0.00002415241],"category_scores_gemma":[0.00002040384,0.0004696042,0.0001002873,0.000720878,0.00004218387,0.0004675006,0.000006335931,0.0007106367,0.00008531113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001577785,"about_ca_system_score_gemma":0.00005618577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007797777,"about_ca_topic_score_gemma":0.00003895022,"domain_scores_codex":[0.9978267,0.0001032668,0.0005966538,0.0005867481,0.0003207361,0.0005659178],"domain_scores_gemma":[0.9989276,0.0002036576,0.00007373866,0.0003014012,0.0000938904,0.0003996893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003840655,0.00003864277,0.00001668911,0.000126291,0.0000485564,0.00004945667,0.004468278,0.8732133,0.1170996,0.00004654949,0.00009747178,0.004756736],"study_design_scores_gemma":[0.002159201,0.0008070619,0.0003253162,0.00161366,0.00004707761,0.00003078301,0.001863934,0.1590878,0.8252293,0.00004363891,0.006833037,0.001959167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3716401,0.000123787,0.625575,0.00005048537,0.0008137393,0.0006927848,0.0001265498,0.0005605905,0.0004169596],"genre_scores_gemma":[0.9990766,0.00002330236,0.0001822724,0.0002171029,0.0001237366,0.0001907047,0.000002628073,0.00008299932,0.0001006256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7141256,"threshold_uncertainty_score":0.9997756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0377382900993719,"score_gpt":0.2473695638933039,"score_spread":0.209631273793932,"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."}}