{"id":"W4205886089","doi":"10.1007/s43674-021-00022-8","title":"Toward durable representations for continual learning","year":2021,"lang":"en","type":"article","venue":"Advances in Computational Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Electronics and Telecommunications Research Institute","keywords":"Forgetting; Computer science; Regularization (linguistics); Ask price; Artificial intelligence; Machine learning; Process (computing); Forcing (mathematics); Metric (unit); Reduction (mathematics); Cognitive psychology; Mathematics; Engineering; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0003088709,0.0001165707,0.000156305,0.0001149642,0.0001777322,0.0001642298,0.0003803027,0.00003782753,0.00005283201],"category_scores_gemma":[0.0007976806,0.0001340183,0.00006945353,0.0006605035,0.0000591561,0.001059651,0.0001090476,0.0001978928,0.00004964118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004965535,"about_ca_system_score_gemma":0.0001534323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005253245,"about_ca_topic_score_gemma":0.00001805867,"domain_scores_codex":[0.9984889,0.0001111763,0.0003904007,0.0004726709,0.0002802115,0.0002566148],"domain_scores_gemma":[0.9977422,0.001492254,0.0001291767,0.0001648212,0.0004074931,0.00006400874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005214891,0.00002944932,0.0005687249,0.00001190694,0.0000042354,0.00001466798,0.00064102,0.6371652,0.00003611951,0.2978607,0.00003085576,0.06363197],"study_design_scores_gemma":[0.0002044249,0.00004440392,0.0009462955,0.00003948071,0.000002169988,0.00003582592,0.001140444,0.7775487,0.001189148,0.1846831,0.03397375,0.0001921967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004624231,0.001373169,0.9915466,0.001291551,0.0004072449,0.0001469362,0.000002444385,0.0001061607,0.004663431],"genre_scores_gemma":[0.6008331,0.0001930239,0.3976533,0.0003446294,0.00004226874,0.00005168838,0.00003318132,0.000008114821,0.0008406522],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6003707,"threshold_uncertainty_score":0.5465107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04618450496025814,"score_gpt":0.3526436579651573,"score_spread":0.3064591530048992,"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."}}