{"id":"W4226165407","doi":"10.1109/cogmi52975.2021.00013","title":"Impact Patterns of Combining Model Pruning and Continual Learning on Model Performance","year":2021,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Pruning; Computer science; Machine learning; Artificial intelligence; Software deployment","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002716181,0.0001236239,0.0001838837,0.00008260786,0.0001415992,0.0001137656,0.0001917686,0.00004309378,0.00001848298],"category_scores_gemma":[0.00006088502,0.0001127974,0.00004936604,0.0001467493,0.00002058921,0.0004245201,0.000178148,0.0002545022,0.000004837075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001952593,"about_ca_system_score_gemma":0.00009899514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000775926,"about_ca_topic_score_gemma":0.000001922951,"domain_scores_codex":[0.998969,0.00005733942,0.0002151803,0.0002855246,0.0002437271,0.0002291943],"domain_scores_gemma":[0.9993894,0.00009246991,0.0001100977,0.0002107624,0.0001083196,0.00008897822],"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":[0.000009302329,0.00003459289,0.02638869,0.0000170167,0.00001467568,0.000004179456,0.003307986,0.9274584,0.002648505,0.01882451,0.00001501719,0.02127713],"study_design_scores_gemma":[0.0004654777,0.0001139091,0.009585017,0.0000610786,0.000003049593,0.000009748625,0.0002867921,0.987871,0.001313812,0.0001354113,0.00002106848,0.0001336641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5145735,0.00001276375,0.4796678,0.00004739077,0.00001760811,0.00002475338,4.396366e-7,0.00005387463,0.005601896],"genre_scores_gemma":[0.9632801,0.00002577618,0.03365799,0.0001749963,0.000006956114,0.000002221582,0.000003061667,0.00001000692,0.002838866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4487066,"threshold_uncertainty_score":0.4599746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02559435759032219,"score_gpt":0.2689923622871192,"score_spread":0.243398004696797,"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."}}