{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006990481,0.0001188323,0.0001554911,0.00013828,0.00009654678,0.0001612952,0.0003428699,0.00006432888,0.00003209193],"category_scores_gemma":[0.00008431259,0.0001243197,0.00003294281,0.000341708,0.00001580265,0.001093786,0.0001510094,0.0002765924,0.00006660574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004134116,"about_ca_system_score_gemma":0.00004190532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003719166,"about_ca_topic_score_gemma":0.000004763899,"domain_scores_codex":[0.998569,0.0001491981,0.000299194,0.0003791036,0.0002653153,0.0003382438],"domain_scores_gemma":[0.9994095,0.00009488001,0.0001447823,0.0002341041,0.0000545581,0.00006215295],"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":[0.00002242734,0.0001223796,0.1191417,0.00007896192,0.0000267688,0.00001648387,0.01111795,0.5143844,0.04638376,0.2350117,0.0005298471,0.07316367],"study_design_scores_gemma":[0.000474848,0.00004069449,0.001539007,0.00003846791,0.000001280657,0.000002789826,0.0004096867,0.9950633,0.0006539526,0.0006953538,0.0009136655,0.0001669453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2434804,0.00005083762,0.7462654,0.000147423,0.000105675,0.0001560459,2.815387e-7,0.0001861394,0.009607843],"genre_scores_gemma":[0.9674079,0.000002823512,0.02783318,0.0001755486,0.00001695643,0.000006327966,0.00001316649,0.00001373789,0.004530391],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7239274,"threshold_uncertainty_score":0.506961,"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."}}