{"id":"W4220918847","doi":"10.1038/s42256-022-00452-0","title":"Biological underpinnings for lifelong learning machines","year":2022,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":225,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lifelong learning; Computer science; Artificial intelligence; Set (abstract data type); Bridge (graph theory); Biological organism; Perspective (graphical); Cognitive science; Human–computer interaction; Biochemical engineering; Engineering; Psychology; Biology; Biological materials","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":[0.0002506033,0.0001904278,0.0001815339,0.00008472853,0.000448728,0.00002035909,0.0003210554,0.00009995804,0.0001296304],"category_scores_gemma":[0.0002243174,0.0001734803,0.00009771766,0.000288515,0.0000284161,0.00006549495,0.0001566139,0.001718285,0.0000061012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006182606,"about_ca_system_score_gemma":0.000007313412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002415942,"about_ca_topic_score_gemma":0.000001644414,"domain_scores_codex":[0.9990201,0.00004759667,0.0002140397,0.0002700059,0.0001430156,0.000305262],"domain_scores_gemma":[0.9993679,0.0003776719,0.00004397264,0.0001256623,0.00002741232,0.00005739606],"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":[0.00005938659,0.00001973424,0.001092804,0.00004847387,0.00002462629,0.00001931849,0.0002162523,0.8722271,0.009721805,0.003733508,0.0003969866,0.11244],"study_design_scores_gemma":[0.0002169797,0.0004582188,0.000393929,0.00002794297,0.00001619207,0.0001721604,0.0002332971,0.8128912,0.05460096,0.01279245,0.117441,0.0007555996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2925585,0.009771495,0.6908637,0.0005114903,0.002282123,0.0005485108,0.0000369194,0.001674221,0.001753061],"genre_scores_gemma":[0.995919,0.00005506483,0.00303233,0.0004501233,0.0002194212,0.00004972818,0.0000387588,0.00003548243,0.000200057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7033606,"threshold_uncertainty_score":0.7465191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01665808754806814,"score_gpt":0.2798211724249318,"score_spread":0.2631630848768636,"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."}}