{"id":"W2794596664","doi":"10.48550/arxiv.1803.11241","title":"Improve the performance of transfer learning without fine-tuning using dissimilarity-based multi-view learning for breast cancer histology images","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Transfer of learning; Feature (linguistics); Artificial intelligence; Extractor; Computer science; Deep learning; Context (archaeology); Breast cancer; Pattern recognition (psychology); Random forest; Machine learning; Cancer; Medicine; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001402516,0.001473218,0.0009107878,0.001009337,0.0003242667,0.0007560891,0.001154672,0.00132109,0.002679787],"category_scores_gemma":[0.004618165,0.0002814184,0.0009144102,0.0005253197,0.0003251697,0.001620415,0.001197303,0.001396918,0.00127321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006138717,"about_ca_system_score_gemma":0.0007490626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005770332,"about_ca_topic_score_gemma":0.005402757,"domain_scores_codex":[0.999206,0.0001194016,0.00004513336,0.0002793313,0.0001908096,0.0001593143],"domain_scores_gemma":[0.9991411,0.0002647204,0.00007641249,0.0002124971,0.0002162929,0.00008888509],"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":[0.001394053,0.0008583703,0.01223038,0.0002239079,0.0003226721,0.0002421807,0.0000757917,0.2065032,0.04187428,0.001011843,0.01077025,0.7244929],"study_design_scores_gemma":[0.00003395557,0.0002237518,0.003129457,0.00001020277,0.00002969299,0.00009516075,0.00002561962,0.9792079,0.01550888,0.0009471818,0.0007716549,0.00001647369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6389015,0.0034461,0.3346814,0.0009502909,0.0005506382,0.0002134944,0.0009821324,0.01352269,0.006751717],"genre_scores_gemma":[0.9191908,0.0002417605,0.07458172,0.000308136,0.00006973188,0.00004746267,0.001979289,0.0002189887,0.00336211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005770332,"threshold_uncertainty_score":0.01147348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06915254186653698,"score_gpt":0.231507616544222,"score_spread":0.162355074677685,"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."}}