{"id":"W4400479983","doi":"10.48550/arxiv.2407.04964","title":"ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Zero (linguistics); Overhead (engineering); Artificial neural network; Binary number; Computer science; Mathematics; Algorithm; Arithmetic; Artificial intelligence; Operating system","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":[0.0004553376,0.0005489585,0.0002652933,0.0003150705,0.0002422806,0.0007594585,0.001781157,0.0004490283,0.002566454],"category_scores_gemma":[0.001547075,0.0002423691,0.0002142549,0.000151364,0.0004435416,0.001020924,0.0006079855,0.0009150417,0.0005712024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007202682,"about_ca_system_score_gemma":0.0006766559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002217207,"about_ca_topic_score_gemma":0.003766855,"domain_scores_codex":[0.9996651,0.0000505904,0.00002548845,0.00007447237,0.0001392702,0.00004501917],"domain_scores_gemma":[0.9996203,0.00008581671,0.00008718001,0.00007158011,0.0001132386,0.00002188123],"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":[0.0007559799,0.0001798548,0.002803117,0.0009011622,0.0001146224,0.0003930777,0.0002771913,0.4280954,0.1981052,0.0377197,0.00823356,0.3224212],"study_design_scores_gemma":[0.00005830552,0.0002752035,0.0007708144,0.00006204679,0.00004018608,0.0001587554,0.00002381789,0.9101235,0.07190239,0.007010994,0.009546378,0.00002762489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06811363,0.001050158,0.9181225,0.0003784852,0.0002368866,0.0001543021,0.000237889,0.004226675,0.007479396],"genre_scores_gemma":[0.865015,0.0002561979,0.1313338,0.0002355953,0.00002436059,0.000180719,0.000196624,0.0002058062,0.002551963],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002566454,"threshold_uncertainty_score":0.008585632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0815489315809812,"score_gpt":0.187385735370032,"score_spread":0.1058368037890508,"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."}}