{"id":"W4379115853","doi":"10.23919/date56975.2023.10136955","title":"Hardware Efficient Weight-Binarized Spiking Neural Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Spiking neural network; MNIST database; Computer science; Artificial neural network; Bottleneck; Perceptron; Spike (software development); Encoder; Artificial intelligence; Layer (electronics); Multilayer perceptron; Computer hardware; Embedded system","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.00007815618,0.0001325438,0.0001302415,0.00006651604,0.0001148954,0.00002391108,0.000111052,0.00004343456,0.00005337215],"category_scores_gemma":[0.00001260443,0.0001191508,0.00005911318,0.000412283,0.0000114373,0.00005449435,0.00006542356,0.0001912149,0.00008808106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002179768,"about_ca_system_score_gemma":0.000001689976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.659022e-7,"about_ca_topic_score_gemma":6.935176e-7,"domain_scores_codex":[0.9992171,0.00001174511,0.0001503852,0.0001591858,0.00009488343,0.0003666826],"domain_scores_gemma":[0.9996802,0.00007865955,0.00001325724,0.0001485146,0.00001258072,0.00006673807],"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":[0.000003803455,0.000002304471,0.00005648827,0.00001357925,0.000005136595,0.00003803821,0.00003655859,0.9873559,0.004174706,0.0001511687,0.0005712791,0.007591048],"study_design_scores_gemma":[0.0001988755,0.00001101973,0.0005126206,0.00001577095,0.000004003206,0.000007724821,0.00002402346,0.99365,0.004141126,0.0000376916,0.001241242,0.0001558788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8996351,0.0001343216,0.0912201,0.00006806192,0.001600973,0.0001331989,8.161354e-7,0.00351364,0.003693839],"genre_scores_gemma":[0.9988579,0.00001281122,0.0003248165,0.00006611025,0.0002457128,0.000005681167,0.000007307856,0.00003242125,0.0004472642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09922282,"threshold_uncertainty_score":0.4858829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01513666082765532,"score_gpt":0.2280802787711019,"score_spread":0.2129436179434466,"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."}}