{"id":"W2776179661","doi":"10.1007/978-3-319-71249-9_27","title":"Crossprop: Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Stochastic gradient descent; Gradient descent; Representation (politics); Artificial intelligence; Meta learning (computer science); Artificial neural network; Domain (mathematical analysis); Feature (linguistics); Scaling; Algorithm; Machine learning; Mathematics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001307303,0.0005766271,0.0007221777,0.000717767,0.0008027744,0.001630128,0.003151304,0.0002667629,0.00003912489],"category_scores_gemma":[0.0003552078,0.0005275632,0.0002390846,0.0003953037,0.0007906005,0.000803891,0.001194422,0.001813533,0.00002932605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003082944,"about_ca_system_score_gemma":0.000243818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009331717,"about_ca_topic_score_gemma":0.0001719633,"domain_scores_codex":[0.9955391,0.0001241702,0.0006811271,0.001767188,0.0009951992,0.0008932385],"domain_scores_gemma":[0.9969648,0.0005971828,0.0005846263,0.001404071,0.0001994466,0.0002498653],"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":[0.000004729793,0.00002153301,0.00006781885,0.000007620245,0.00002559743,0.00006229363,0.0006831837,0.7831421,0.00001782691,0.002051116,0.00002493966,0.2138912],"study_design_scores_gemma":[0.0003253077,0.00009609274,0.0002768723,0.0001097276,0.00003183591,0.00004148528,6.739081e-7,0.9905503,0.00001586682,0.006637434,0.001373628,0.0005407594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005502278,0.001512435,0.994417,0.0007891717,0.00134529,0.0004598884,0.000002680321,0.0001550781,0.001263411],"genre_scores_gemma":[0.9202136,0.00005381699,0.07631039,0.001008675,0.0003019636,0.00004840935,0.00002123186,0.00006228777,0.001979645],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9201586,"threshold_uncertainty_score":0.9997176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03854797923379474,"score_gpt":0.284209923196719,"score_spread":0.2456619439629243,"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."}}