{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00164672,0.001008097,0.001238593,0.000503408,0.0004133875,0.0006816568,0.002372307,0.002052902,0.00234926],"category_scores_gemma":[0.003340665,0.0005874878,0.0006285632,0.0006092692,0.0007552512,0.001807227,0.001880326,0.003005139,0.0006561255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006221436,"about_ca_system_score_gemma":0.0006727746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00249838,"about_ca_topic_score_gemma":0.004759826,"domain_scores_codex":[0.9995431,0.0001374012,0.00002055968,0.0001709862,0.00005909718,0.0000688927],"domain_scores_gemma":[0.9986406,0.0008481214,0.00006617009,0.0002278989,0.0001313764,0.0000857982],"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":[0.0006658412,0.0005721953,0.001254294,0.0002522115,0.0002596491,0.0001726969,0.0001071584,0.3349795,0.03489126,0.01663972,0.00708569,0.6031197],"study_design_scores_gemma":[0.00001166173,0.00006279159,0.0002218498,0.000007365052,0.00001393949,0.00003244167,0.000006771416,0.9871432,0.004076725,0.007902313,0.0005120933,0.00000884221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02348356,0.0006550422,0.9732289,0.0001918047,0.00008975512,0.00004288804,0.00009423388,0.0009458399,0.001268109],"genre_scores_gemma":[0.7384486,0.0004013547,0.2530618,0.000432035,0.0001501191,0.0001783966,0.0006090048,0.0002419885,0.006476741],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00249838,"threshold_uncertainty_score":0.008708775,"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."}}