{"id":"W4226227766","doi":"10.1109/tcsii.2022.3157789","title":"CODEX: Stochastic Encoding Method to Relax Resistive Crossbar Accelerator Design Requirements","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits & Systems II Express Briefs","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Encoding (memory); Reduction (mathematics); Thresholding; Range (aeronautics); Effective number of bits; Gaussian; Artificial intelligence; Computer hardware; Algorithm; Image (mathematics); Electronic engineering; Mathematics; CMOS; Engineering","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0006955218,0.0004128875,0.0004938309,0.0003023106,0.001860677,0.000119131,0.0004703968,0.00009392481,0.0000868733],"category_scores_gemma":[0.00001849613,0.0004967942,0.0001386404,0.0006331005,0.00002879875,0.0003852718,0.00001397505,0.0007340566,0.00003362371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000589939,"about_ca_system_score_gemma":0.00006362007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003223263,"about_ca_topic_score_gemma":0.000002112984,"domain_scores_codex":[0.9969627,0.0004396724,0.0006569241,0.0006745165,0.0006108428,0.0006554009],"domain_scores_gemma":[0.9985076,0.0004895532,0.0001122839,0.0005341917,0.00008768706,0.0002687119],"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":[0.00004695854,0.00004757277,2.812877e-7,0.00006320227,0.00006532147,0.0000258409,0.001647524,0.7645441,0.2303877,0.00003656861,0.0004124483,0.002722429],"study_design_scores_gemma":[0.003583351,0.001682151,0.00003857784,0.00123152,0.0003073296,0.0004827474,0.00332229,0.2238132,0.742568,0.0001444015,0.01961567,0.003210794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01497656,0.0001969949,0.9793772,0.00001952531,0.002939493,0.001195108,0.0001761367,0.0007787464,0.000340206],"genre_scores_gemma":[0.9954373,0.000003976681,0.002299865,0.0001188414,0.0001610122,0.0008739397,0.000003682884,0.0001281097,0.0009732283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9804608,"threshold_uncertainty_score":0.9997483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.061229102749464,"score_gpt":0.2913411391087209,"score_spread":0.2301120363592569,"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."}}