{"id":"W2152659120","doi":"10.1177/1059712309342487","title":"Incremental Learning and Memory Consolidation of Whole Body Human Motion Primitives","year":2009,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Japan Society for the Promotion of Science","keywords":"Incremental learning; Computer science; Consolidation (business); Artificial intelligence; Memory consolidation; Motion (physics); Hierarchy; Motor skill; Machine learning; Psychology","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":[0.0001070295,0.00007476092,0.00009151922,0.00009464533,0.0001457753,0.00003854512,0.00007370304,0.00003517106,0.00002898692],"category_scores_gemma":[0.000007406337,0.00007908243,0.0000267142,0.00007549879,0.00004403545,0.0005371638,0.00003236088,0.00009320682,0.00001184313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002293482,"about_ca_system_score_gemma":0.00001004278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001270568,"about_ca_topic_score_gemma":0.000002269495,"domain_scores_codex":[0.9993787,0.00006443669,0.0001487696,0.0001836323,0.0001311151,0.00009329847],"domain_scores_gemma":[0.9996858,0.00001552367,0.0001138803,0.00007378693,0.00007551185,0.00003551468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000009058548,0.0003305337,0.003212619,0.000004305649,0.000008737294,0.000007867924,0.0009239426,0.000003432326,0.7407531,0.00831694,0.00003850413,0.246391],"study_design_scores_gemma":[0.0007173186,0.0009201413,0.6697163,0.00004479285,0.00004246039,0.00001824721,0.0007159012,0.000681309,0.3261068,0.000724208,0.0001104708,0.0002020239],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9776369,0.00002155527,0.02012422,0.00004368433,0.00003578973,0.0001684722,0.000002561713,0.00006185887,0.001904982],"genre_scores_gemma":[0.9983001,0.000004365064,0.0014295,0.00003595106,0.00002412782,0.000009684341,0.00001607739,0.00000315793,0.0001770218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6665037,"threshold_uncertainty_score":0.3224888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02679972958699365,"score_gpt":0.2890491270989224,"score_spread":0.2622493975119287,"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."}}