{"id":"W7061864601","doi":"","title":"The role of continual learning and adaptive computation in improving computational efficiency of deep learning","year":2024,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Particle accelerators and beam dynamics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Oak Ridge National Laboratory; Fonds de recherche du Québec – Nature et technologies; Université de Montréal; Deutscher Akademischer Austauschdienst; Canadian Institute for Advanced Research; Canada Excellence Research Chairs, Government of Canada; U.S. Department of Energy","keywords":"Deep learning; Agrégation; Context (archaeology)","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":[0.002054317,0.0005851232,0.0004606849,0.0006541315,0.0004549439,0.001327293,0.001589699,0.0008652836,0.002531128],"category_scores_gemma":[0.007310335,0.0003759549,0.0003820252,0.0006222566,0.001670182,0.003010748,0.002077745,0.00160074,0.000369251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008697353,"about_ca_system_score_gemma":0.0009902337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0027819,"about_ca_topic_score_gemma":0.004205565,"domain_scores_codex":[0.9993705,0.0001924974,0.00004093756,0.0001487513,0.0001606898,0.00008653639],"domain_scores_gemma":[0.9967732,0.001881163,0.0001708969,0.0007105435,0.0003402352,0.0001240298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003723493,0.0002586608,0.004893363,0.0002237339,0.00008321354,0.0001178694,0.0004562621,0.4425203,0.02182339,0.05032234,0.001484963,0.4774435],"study_design_scores_gemma":[0.00001645007,0.00009952456,0.0005645308,0.00002422415,0.00001349723,0.00004085988,0.00003997072,0.9777372,0.005833629,0.01374445,0.001874491,0.00001109962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1974889,0.002079243,0.7837916,0.001144703,0.0001398156,0.00008444616,0.00004111603,0.00146262,0.01376758],"genre_scores_gemma":[0.8410689,0.0005149157,0.1537331,0.000147237,0.00006671071,0.00007404617,0.00003551683,0.0001309663,0.004228593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0027819,"threshold_uncertainty_score":0.01086438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0024186234982556,"score_gpt":0.1658620512045735,"score_spread":0.1634434277063179,"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."}}