{"id":"W2977479414","doi":"10.1109/ijcnn.2019.8852426","title":"Preempting Catastrophic Forgetting in Continual Learning Models by Anticipatory Regularization","year":2019,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Forgetting; Computer science; Regularization (linguistics); Artificial intelligence; Discriminative model; Machine learning; Task (project management); Anticipation (artificial intelligence); Artificial neural network; Cognitive psychology; Engineering","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":[0.00241577,0.001086295,0.0009600295,0.0003570114,0.0003551129,0.001004763,0.002327885,0.001506217,0.001458228],"category_scores_gemma":[0.006873194,0.0005907799,0.0007520496,0.0003420731,0.001958566,0.002273956,0.001556144,0.003241437,0.0003566966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008409299,"about_ca_system_score_gemma":0.001065135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003611282,"about_ca_topic_score_gemma":0.005090836,"domain_scores_codex":[0.9995089,0.0001613675,0.00002935668,0.0001209649,0.00009329088,0.0000862288],"domain_scores_gemma":[0.997227,0.001421937,0.0003671944,0.0005146476,0.0002899784,0.0001792738],"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":[0.0001446059,0.0001533086,0.001449614,0.00007142607,0.00007528881,0.0001115318,0.0001588515,0.9412889,0.003566285,0.01995295,0.001119698,0.03190742],"study_design_scores_gemma":[0.000008016837,0.00002386341,0.00007217274,0.000004630834,0.000005826203,0.00001003249,0.000003868096,0.9918711,0.0003655537,0.007476667,0.0001535321,0.000004707326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09625175,0.0004385151,0.8983759,0.0008819949,0.00008577602,0.00005815082,0.00004082628,0.0008375807,0.003029568],"genre_scores_gemma":[0.9309462,0.0003183366,0.06224909,0.0003462468,0.00009031104,0.0001437662,0.00009244875,0.0001275519,0.005686018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003611282,"threshold_uncertainty_score":0.01277602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01633576027562482,"score_gpt":0.2232339221020295,"score_spread":0.2068981618264047,"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."}}