{"id":"W4382319506","doi":"10.48550/arxiv.2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; DeepMind; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"MNIST database; Backpropagation; Artificial intelligence; Computer science; Plasticity; Deep learning; Normalization (sociology); Regularization (linguistics); Machine learning; Artificial neural network; Task (project management); Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001649058,0.0005129828,0.0006547952,0.0005025498,0.0005773189,0.0009805766,0.001913069,0.0009537921,0.001282662],"category_scores_gemma":[0.007841215,0.0004732224,0.0004251465,0.0004667397,0.00265256,0.003558479,0.00251365,0.002323682,0.0004024791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008080647,"about_ca_system_score_gemma":0.0007820838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001281852,"about_ca_topic_score_gemma":0.001226355,"domain_scores_codex":[0.9994125,0.0001226297,0.00003485434,0.0001929196,0.0001554631,0.00008148405],"domain_scores_gemma":[0.9974251,0.001146244,0.0002558773,0.0007021949,0.0003025259,0.0001681929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004970999,0.0004349473,0.005328384,0.000287668,0.0001172999,0.0003833631,0.0006197452,0.556007,0.05318497,0.1106567,0.003339159,0.2691437],"study_design_scores_gemma":[0.00002032453,0.000121893,0.0009596014,0.00002412594,0.00001299675,0.0001304609,0.0000453308,0.8678712,0.01218837,0.1168489,0.001751732,0.00002499435],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2582986,0.0009039765,0.730953,0.001496735,0.00009982827,0.00007342625,0.0001470304,0.002428911,0.005598345],"genre_scores_gemma":[0.932651,0.0002819301,0.06390341,0.0001938191,0.00004525027,0.00008367933,0.0001302315,0.0001408093,0.002569909],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001913069,"threshold_uncertainty_score":0.008721113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09071131042013264,"score_gpt":0.2010276352872427,"score_spread":0.11031632486711,"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."}}