{"id":"W7011573803","doi":"","title":"Meta-learning for Clinical and Imaging Data Fusion for Improved Deep Learning Inference","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; International Progressive MS Alliance; F. Hoffmann-La Roche; Teva Pharmaceutical Industries; Western Canada Research Grid; Biogen","keywords":"Deep learning; Inference; Sensor fusion; Pattern recognition (psychology); Fusion; Artificial neural network","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":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006126634,0.0008282594,0.001300023,0.0005107707,0.002641603,0.0007521918,0.002397168,0.0005980134,0.00003208342],"category_scores_gemma":[0.01115371,0.0008486709,0.0005756044,0.0006722681,0.00008811543,0.002116952,0.001152333,0.002437446,0.00006551419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001157166,"about_ca_system_score_gemma":0.0001134047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006778503,"about_ca_topic_score_gemma":0.0003170977,"domain_scores_codex":[0.9934533,0.000789271,0.001541111,0.002617782,0.0005967513,0.001001844],"domain_scores_gemma":[0.9920116,0.004191109,0.001291923,0.001335053,0.0007301262,0.0004401904],"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":[0.0001799722,0.00006845401,0.0001065947,0.0003658123,0.000748969,0.00001152641,0.00006232732,0.0002754788,0.002669428,0.02609919,0.00001258365,0.9693997],"study_design_scores_gemma":[0.003717583,0.0005930393,0.002382114,0.0004022965,0.00215229,0.00002079707,0.001352945,0.5735478,0.0008098148,0.02262542,0.3899539,0.002441929],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5698326,0.023778,0.2259588,0.002529474,0.05556655,0.04012706,0.005811125,0.02748571,0.04891066],"genre_scores_gemma":[0.7256887,0.004362133,0.2168141,0.001231374,0.0004935135,0.001699668,0.01446338,0.0009905179,0.03425662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9669577,"threshold_uncertainty_score":0.999864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1265240776760219,"score_gpt":0.3607896563501661,"score_spread":0.2342655786741442,"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."}}