{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001419092,0.0004697819,0.0005482904,0.0002138595,0.00009145218,0.00004388639,0.0004319109,0.000267813,0.0000181592],"category_scores_gemma":[0.000009610795,0.0004823398,0.0001763256,0.0005381807,0.00009798109,0.0001605525,0.0004678426,0.001126832,0.00001363181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001145633,"about_ca_system_score_gemma":0.00004921365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002605829,"about_ca_topic_score_gemma":0.000004695387,"domain_scores_codex":[0.9983914,0.0001031707,0.0002785662,0.0006872918,0.0000799859,0.0004595437],"domain_scores_gemma":[0.9989136,0.0002341688,0.0001270414,0.0005191537,0.00006824448,0.0001377768],"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":[0.0003281526,0.0000194666,0.00008266845,0.0003193075,0.0001885342,0.001029248,0.0000473375,0.9957748,0.001460415,0.0003657637,0.0001009884,0.0002833338],"study_design_scores_gemma":[0.0004867774,0.0001459068,0.00003109328,0.0003602041,0.0002077543,0.00002295646,0.00003607593,0.9914942,0.004336344,0.002355407,0.000008896057,0.0005144103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6191481,0.0004346095,0.3790639,0.000003780993,0.0005004044,0.0002766887,0.000008981187,0.0004054513,0.000158092],"genre_scores_gemma":[0.9962229,0.0002436003,0.003150274,0.00001831144,0.0000434552,0.000001324234,0.00001776554,0.00009114353,0.0002112827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3770747,"threshold_uncertainty_score":0.9997628,"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."}}