{"id":"W2998655644","doi":"10.1609/aaai.v34i04.5884","title":"Residual Continual Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Residual; Forgetting; Computer science; Normalization (sociology); Artificial intelligence; Task (project management); Machine learning; Learning network; Convolutional neural network; Deep learning; Artificial neural network; Algorithm; 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":[0.0004354212,0.0001875449,0.0002396175,0.00006949082,0.000247853,0.0003315926,0.001754811,0.0000729434,0.000120184],"category_scores_gemma":[0.001202009,0.0001490678,0.0000998429,0.0006706677,0.0001916413,0.0004250428,0.0004095258,0.0005300545,0.0002690192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001925404,"about_ca_system_score_gemma":0.00008459418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009954993,"about_ca_topic_score_gemma":0.000001424864,"domain_scores_codex":[0.9981608,0.000035254,0.0004698501,0.0004714927,0.0005466919,0.0003158664],"domain_scores_gemma":[0.9987586,0.0001109188,0.0003678181,0.0001536357,0.0004601618,0.0001488725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005299094,0.00003729076,0.0002754972,0.00001911523,0.00001053983,8.657245e-7,0.005310518,0.0002966559,0.03716529,0.885231,0.0003390175,0.07126127],"study_design_scores_gemma":[0.0001139743,0.0007971079,0.0006825771,0.0002113477,0.00001902505,0.000007623984,0.005422289,0.3449605,0.5812761,0.05925365,0.006654328,0.0006015165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3294785,0.0001027066,0.3775799,0.09654629,0.001303797,0.001311972,0.00000631809,0.001238675,0.1924318],"genre_scores_gemma":[0.9939589,0.00001420086,0.004402552,0.001014968,0.000112229,0.000008539853,3.349897e-7,0.00001188439,0.0004764225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8259773,"threshold_uncertainty_score":0.6078808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1016628254990642,"score_gpt":0.2867960757735737,"score_spread":0.1851332502745094,"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."}}