{"id":"W3200693755","doi":"10.1007/978-3-030-86486-6_38","title":"Continual Learning with Dual Regularizations","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; Carleton University","funders":"","keywords":"Computer science; Forgetting; Interleaving; Dual (grammatical number); Artificial intelligence; Set (abstract data type); Representation (politics); Machine learning; Process (computing); Key (lock)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006810278,0.0004337985,0.0004523153,0.0006093568,0.0004872592,0.001030425,0.001387417,0.000238655,0.00007346881],"category_scores_gemma":[0.0001767362,0.0003954627,0.00009268709,0.0009164159,0.0005830941,0.0006318624,0.0008203263,0.001195399,0.00004378341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603838,"about_ca_system_score_gemma":0.0008660391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007838315,"about_ca_topic_score_gemma":0.00005554549,"domain_scores_codex":[0.9964454,0.00007608317,0.0004140901,0.001394423,0.001089097,0.0005809559],"domain_scores_gemma":[0.9977704,0.000414527,0.000305238,0.0008844269,0.0004368977,0.0001884858],"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":[0.000007858232,0.00003289128,0.0001769583,0.00002618681,0.00002947209,0.0005128345,0.002429489,0.2446324,0.0002734966,0.1916125,0.00002258562,0.5602434],"study_design_scores_gemma":[0.0008421688,0.0004099222,0.0005259339,0.0007762486,0.00002060857,0.0004803493,0.000004114152,0.9421138,0.0005709102,0.02266321,0.03018433,0.001408434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007265054,0.0002568457,0.9860454,0.0008068932,0.0006771725,0.0002020811,0.000001235553,0.0002439963,0.01169373],"genre_scores_gemma":[0.1288085,0.00003904474,0.8561723,0.001774126,0.0005065125,0.00001158543,0.00002622889,0.00007122626,0.01259048],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6974814,"threshold_uncertainty_score":0.9998497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01298865307760288,"score_gpt":0.2265503314633705,"score_spread":0.2135616783857676,"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."}}