{"id":"W4387004586","doi":"10.1016/j.eswa.2023.121734","title":"Transformer-BLS: An efficient learning algorithm based on multi-head attention mechanism and incremental learning algorithms","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"MNIST database; Computer science; Transformer; Algorithm; Artificial intelligence; Machine learning; Pattern recognition (psychology); Artificial neural network; Voltage","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":[0.0007004377,0.0002474383,0.0002260494,0.0002919569,0.0009727303,0.0002611734,0.0003559129,0.0000913446,0.00000440001],"category_scores_gemma":[0.00001220691,0.0002129342,0.00004835947,0.0007330542,0.0000423224,0.000183796,0.00004412971,0.0003170859,0.0001159105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007345086,"about_ca_system_score_gemma":0.0000435894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004620968,"about_ca_topic_score_gemma":0.000008740453,"domain_scores_codex":[0.9978421,0.0002508335,0.0002920826,0.0007235656,0.0004860305,0.0004053655],"domain_scores_gemma":[0.9990609,0.00009911053,0.0001352005,0.0004224308,0.00007669999,0.0002056943],"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":[0.00004020004,0.0010755,0.00181277,0.0001781922,0.0001061223,0.00003210124,0.00975921,0.3852336,0.01062016,0.02959343,0.0001569992,0.5613917],"study_design_scores_gemma":[0.0008882235,0.0003806831,0.0009776581,0.00008159027,0.000006383696,0.00002144183,0.001093012,0.9880634,0.000168162,0.00001207997,0.008029,0.00027837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01478666,0.00008139542,0.9824474,0.0003371356,0.0001188438,0.0008253353,0.000004684311,0.00111423,0.0002843257],"genre_scores_gemma":[0.9323691,0.00001830123,0.06495287,0.00008025416,0.0001527132,0.001478745,0.0001351221,0.00004751892,0.0007653759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9175825,"threshold_uncertainty_score":0.8683203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01990274320579866,"score_gpt":0.2876513255205417,"score_spread":0.2677485823147431,"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."}}