{"id":"W2895195933","doi":"10.1007/978-3-030-18305-9_66","title":"Generating Accurate Virtual Examples for Lifelong Machine Learning","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Restricted Boltzmann machine; Artificial intelligence; Task (project management); Machine learning; Set (abstract data type); Lifelong learning; Boltzmann machine; Training set; Artificial neural network","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001545942,0.0005816294,0.0005952148,0.0007207833,0.0006203688,0.001185338,0.002540284,0.0002962988,0.00003352591],"category_scores_gemma":[0.0004466757,0.0005514493,0.0001849406,0.0004501904,0.0002929339,0.0008224855,0.001053651,0.001109742,0.00007661511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002033954,"about_ca_system_score_gemma":0.0006832061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001883478,"about_ca_topic_score_gemma":0.00005940041,"domain_scores_codex":[0.9959477,0.00007623103,0.000644039,0.001665671,0.0008658327,0.0008005127],"domain_scores_gemma":[0.9966736,0.001451708,0.0005098776,0.0008876479,0.0002902037,0.0001869161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006181423,0.000008329296,0.00005441514,0.00002584901,0.00001082493,0.00001381031,0.00089105,0.4731032,0.0004225166,0.02558375,0.00001211584,0.499868],"study_design_scores_gemma":[0.0004279396,0.0002754831,0.0000367949,0.0002040342,0.000006351818,0.00003063132,7.963245e-7,0.9760064,0.0003008085,0.006997486,0.01504736,0.0006658488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000150735,0.0004826542,0.9946446,0.0004768148,0.002025358,0.0005565335,0.000005890786,0.0002642424,0.001393166],"genre_scores_gemma":[0.09991903,0.00006445441,0.8912632,0.003026955,0.001028543,0.00002172043,0.00004087214,0.00009225165,0.004542918],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5029033,"threshold_uncertainty_score":0.9998515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03258662774635546,"score_gpt":0.263475812019237,"score_spread":0.2308891842728815,"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."}}