{"id":"W3127129507","doi":"","title":"Incremental few-shot learning via vector quantization in deep embedded space","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Forgetting; Overfitting; Learning vector quantization; Computer science; Artificial intelligence; Regularization (linguistics); Machine learning; Quantization (signal processing); Incremental learning; Support vector machine; Deep learning; Reproducing kernel Hilbert space; Vector quantization; Kernel (algebra); Pattern recognition (psychology); Artificial neural network; Algorithm; Mathematics; Hilbert space","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004235792,0.0002221542,0.0002147881,0.0004294666,0.0003288959,0.0006267849,0.000617152,0.00009790132,0.001211619],"category_scores_gemma":[0.0012403,0.0002631466,0.0001022096,0.0008134986,0.00006177299,0.0008350495,0.0002503374,0.0008047812,0.000381577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001938363,"about_ca_system_score_gemma":0.0002035913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001232909,"about_ca_topic_score_gemma":0.0001462135,"domain_scores_codex":[0.9970813,0.0005653178,0.0004873026,0.000734827,0.0007920592,0.0003392085],"domain_scores_gemma":[0.9983792,0.0003667818,0.0002814746,0.0003304014,0.0005164876,0.0001256187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000787325,0.0004528345,0.07750378,0.00001849234,0.000133883,0.0002989361,0.01535898,0.2102705,0.06171115,0.5972294,0.000143911,0.03679938],"study_design_scores_gemma":[0.001129232,0.0001042401,0.0517048,0.0001000844,0.000008060953,0.00005326228,0.004130879,0.9327525,0.003621521,0.002240414,0.003754246,0.0004007769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1128116,0.00006028738,0.7700199,0.0076736,0.001219807,0.0002808157,0.00000264515,0.0004689672,0.1074624],"genre_scores_gemma":[0.9840883,0.00006357382,0.01042651,0.0002557852,0.0000974249,0.00004530342,0.0001606301,0.00002339234,0.004839083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8712767,"threshold_uncertainty_score":0.9999821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05821540092947535,"score_gpt":0.3431383331195025,"score_spread":0.2849229321900272,"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."}}