{"id":"W4387185222","doi":"10.3233/faia230370","title":"Evolving Dictionary Representation for Few-Shot Class-Incremental Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Carleton University","funders":"","keywords":"Computer science; Forgetting; Artificial intelligence; Class (philosophy); Representation (politics); Machine learning; Session (web analytics); Process (computing); Adaptation (eye); Key (lock); Feature (linguistics)","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"],"consensus_categories":[],"category_scores_codex":[0.000402687,0.0002432915,0.0002818359,0.0004578462,0.0004920178,0.0002558914,0.0004275869,0.0002074059,0.00002912568],"category_scores_gemma":[0.00007890275,0.0002916951,0.0001161974,0.0002684853,0.0001388008,0.0003411692,0.0001558089,0.0004487211,0.0001110606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001264724,"about_ca_system_score_gemma":0.00007445157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001581682,"about_ca_topic_score_gemma":0.00002447394,"domain_scores_codex":[0.9980549,0.00003209557,0.0005971031,0.0007484491,0.0002833442,0.0002841754],"domain_scores_gemma":[0.998919,0.0002428763,0.0002698697,0.0003429927,0.0001258202,0.00009948546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000123252,0.00002075066,0.0001213102,0.0000243984,0.0000288175,0.000002458277,0.0004405361,0.002468379,0.00007498566,0.6775107,0.002114387,0.317181],"study_design_scores_gemma":[0.00006584162,0.00007212475,0.00008316131,0.0001041039,0.00002780994,0.000004380939,0.001278763,0.3154603,0.0002231963,0.5030909,0.1791363,0.0004531793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00000561158,0.00034733,0.9512435,0.0006233104,0.0005392779,0.000902049,0.00001442798,0.0002427424,0.04608173],"genre_scores_gemma":[0.06360112,0.005593871,0.3376309,0.0009844556,0.002647315,0.00436883,0.001571582,0.000408371,0.5831936],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6136127,"threshold_uncertainty_score":0.9999535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09085757404646855,"score_gpt":0.3159019860949666,"score_spread":0.225044412048498,"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."}}