{"id":"W4392931151","doi":"10.1016/j.knosys.2024.111653","title":"Approximate and Memorize (A&M) : Settling opposing views in replay-based continuous unsupervised domain adaptation","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Memorization; Stability (learning theory); Computer science; Adaptation (eye); Forgetting; Scalability; Artificial intelligence; Domain (mathematical analysis); Machine learning; Theoretical computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00245683,0.0007524596,0.001205731,0.0004317027,0.0007120415,0.001320311,0.001910989,0.002127135,0.002136308],"category_scores_gemma":[0.01117645,0.0005812022,0.0005388953,0.0004184565,0.001637036,0.0033049,0.003169543,0.002935105,0.0005240735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000489257,"about_ca_system_score_gemma":0.0009139024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004338258,"about_ca_topic_score_gemma":0.004172881,"domain_scores_codex":[0.9992245,0.0003059525,0.00003457504,0.0002396141,0.0001222891,0.00007300024],"domain_scores_gemma":[0.9956066,0.003190746,0.0002016785,0.0005820442,0.0002591967,0.0001597655],"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":[0.001665765,0.0002730996,0.001800924,0.0002612212,0.0003334277,0.0003294361,0.001495031,0.281143,0.02725984,0.03368859,0.006587842,0.6451618],"study_design_scores_gemma":[0.00002423113,0.00007113191,0.0002584348,0.00001063345,0.00002194878,0.00004228835,0.00006840434,0.9794304,0.004256543,0.01514998,0.0006454017,0.00002058742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03943072,0.0004604341,0.956907,0.0005390196,0.00009444715,0.00004737475,0.00004696933,0.001155943,0.001318033],"genre_scores_gemma":[0.7156119,0.0002623657,0.2799596,0.0005242665,0.0001211593,0.00009866885,0.0001572198,0.0002597742,0.003004963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004338258,"threshold_uncertainty_score":0.0129931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05531971084796615,"score_gpt":0.2890656279337792,"score_spread":0.233745917085813,"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."}}