{"id":"W4382681649","doi":"10.1007/s42979-023-01921-y","title":"EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models","year":2023,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; McGill University; Huawei Technologies (Canada)","funders":"","keywords":"Deep learning; Computer science; Leverage (statistics); Pruning; Artificial intelligence; Computer engineering; Inference; Edge device; Quantization (signal processing); Multiplication (music); Architecture; Computer architecture; Theoretical computer science; Machine learning; Algorithm; Mathematics","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":[0.0006855408,0.0001373719,0.0001569757,0.0002772327,0.0004882106,0.000205422,0.002006161,0.00002827927,0.000001117784],"category_scores_gemma":[0.00006159586,0.0001302579,0.0000421801,0.00209471,0.0002534741,0.001385225,0.0006942537,0.0001144566,0.00001931467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005996272,"about_ca_system_score_gemma":0.0001109469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006848908,"about_ca_topic_score_gemma":0.000003697039,"domain_scores_codex":[0.9980047,0.0000495972,0.0002881523,0.0007518384,0.0004829428,0.0004227865],"domain_scores_gemma":[0.9983864,0.0003101154,0.0001615466,0.0006164549,0.0003813999,0.0001440907],"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":[0.000001517679,0.00002299476,0.00001825784,0.000003886923,0.000001348012,5.435388e-7,0.001002413,0.8055414,0.002012286,0.105786,0.000008184614,0.08560116],"study_design_scores_gemma":[0.0001575065,0.000181903,0.0003667907,0.00001288962,0.000001458614,0.000002369969,0.00001441567,0.9730314,0.005029956,0.02096808,0.00008698448,0.0001462638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04539844,0.00001301505,0.9531942,0.0002118862,0.0003725449,0.0004001765,0.000002173938,0.0002989742,0.0001085789],"genre_scores_gemma":[0.7249153,0.000008181068,0.2748326,0.00009022708,0.00007070603,0.0000588185,0.000004509265,0.000006455719,0.00001317077],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6795169,"threshold_uncertainty_score":0.5311764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0589813603559361,"score_gpt":0.3297820042171644,"score_spread":0.2708006438612283,"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."}}