{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001831292,0.000620394,0.001154155,0.0009951541,0.0006370264,0.00159709,0.002545095,0.001775362,0.004834418],"category_scores_gemma":[0.01095316,0.0006737229,0.0007888753,0.0008985287,0.001812089,0.005631517,0.003767359,0.004370751,0.001011873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009028814,"about_ca_system_score_gemma":0.0006602606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001625189,"about_ca_topic_score_gemma":0.002852683,"domain_scores_codex":[0.9992859,0.0002101721,0.00004983178,0.0002602042,0.0001215168,0.00007248518],"domain_scores_gemma":[0.9945368,0.002796721,0.0003004558,0.001638116,0.0004435231,0.0002845163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002530236,0.0002721595,0.001947146,0.0002823529,0.0001455063,0.0001533719,0.0004987794,0.3108928,0.005262993,0.377575,0.007640255,0.2950766],"study_design_scores_gemma":[0.000008828142,0.0000301667,0.0001367699,0.00002082971,0.0000100413,0.00002715628,0.00003072424,0.7555416,0.0005497485,0.2424641,0.00117124,0.000008846742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02115487,0.0005110297,0.9753571,0.0005551782,0.00007610778,0.00002564106,0.0001489141,0.0006215443,0.001549655],"genre_scores_gemma":[0.7135054,0.0008157373,0.2764278,0.0004543549,0.0002381737,0.0002022062,0.0009352492,0.0003285816,0.007092482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004834418,"threshold_uncertainty_score":0.01617271,"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."}}