{"id":"W4321792452","doi":"10.1016/j.neunet.2023.02.023","title":"Episodic task agnostic contrastive training for multi-task learning","year":2023,"lang":"en","type":"article","venue":"Neural Networks","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Vector Institute; Western University","funders":"National Key Research and Development Program of China; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Multi-task learning; Machine learning; Task (project management); Embedding; Feature learning; Transfer of learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005115844,0.0002071182,0.0002554691,0.0001373003,0.0004776313,0.0002327365,0.0004887375,0.000107112,0.00001099928],"category_scores_gemma":[0.0006284259,0.0002058228,0.0001341219,0.0007348892,0.00006378725,0.0003339684,0.0001328111,0.0004949126,0.00007465715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002857041,"about_ca_system_score_gemma":0.00003227606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006440632,"about_ca_topic_score_gemma":0.000007576257,"domain_scores_codex":[0.9980872,0.0001667832,0.0002976079,0.0005139294,0.0002194764,0.0007149995],"domain_scores_gemma":[0.9980279,0.001350073,0.0001530975,0.0002099027,0.00008319818,0.0001757985],"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":[0.0000225145,0.0000164698,0.000547412,0.000008949592,0.00002377862,0.00004676377,0.002588204,0.7031541,0.0002645873,0.002876508,0.001147048,0.2893037],"study_design_scores_gemma":[0.0009612345,0.000141882,0.006409814,0.00003153924,0.000009712494,0.00001124807,0.0002813788,0.9848413,0.000007443271,0.0001757518,0.006895148,0.0002335647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01021136,0.0001732793,0.9863396,0.0005940081,0.001067928,0.0003762651,0.000002237709,0.000918528,0.0003167719],"genre_scores_gemma":[0.9892668,0.00003091165,0.008405973,0.0008186977,0.0003021804,0.00008691025,0.00003798399,0.0000316933,0.001018915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790554,"threshold_uncertainty_score":0.8393209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06642584105792725,"score_gpt":0.2973511286292233,"score_spread":0.230925287571296,"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."}}