{"id":"W3201645160","doi":"10.1109/ijcnn52387.2021.9533834","title":"Comparative Study on Quantization-Aware Training of Memristor Crossbars for Reducing Inference Power of Neural Networks at The Edge","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Neurosciences Research Foundation","keywords":"Crossbar switch; Computer science; Memristor; Convolutional neural network; Edge computing; Quantization (signal processing); Inference; Edge device; Artificial neural network; Artificial intelligence; Kernel (algebra); Cloud computing; Enhanced Data Rates for GSM Evolution; Computer architecture; Algorithm; Electronic engineering; Engineering; Telecommunications; Mathematics; Operating system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001058237,0.0001122788,0.000250517,0.00002232947,0.0001197166,0.000009402732,0.00009231539,0.00002687021,0.00002777923],"category_scores_gemma":[0.00006149044,0.00008638243,0.0000570679,0.0001785666,0.00003969037,0.00006516346,0.00004135508,0.0001147025,3.797244e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000234877,"about_ca_system_score_gemma":0.0000133492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001657478,"about_ca_topic_score_gemma":0.00002172461,"domain_scores_codex":[0.9992936,0.00003939831,0.0002789414,0.0001493783,0.00008920106,0.0001495405],"domain_scores_gemma":[0.9990193,0.0006003688,0.00007178523,0.0001769872,0.0001072613,0.00002434726],"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":[0.00002830396,0.00003116387,0.0003387103,0.00002064943,0.00002875325,0.000001345472,0.007619698,0.9823467,0.008847597,0.0001368653,0.00007062623,0.0005296625],"study_design_scores_gemma":[0.000642315,0.0003386974,0.003631978,0.00009192708,0.00002603566,0.000003634698,0.01549311,0.8147629,0.164724,0.00003189889,0.00005205625,0.0002014587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9225321,0.000110708,0.07635556,0.00001376815,0.0003055949,0.0002446667,0.000005901399,0.00004627612,0.0003853876],"genre_scores_gemma":[0.9995736,0.000002017612,0.0002471891,0.00002028359,0.00003261024,0.000009163814,0.000006951311,0.00001333566,0.00009485675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1675837,"threshold_uncertainty_score":0.3522573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08475422436098824,"score_gpt":0.3403366109150213,"score_spread":0.255582386554033,"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."}}