{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001524896,0.001442378,0.001561899,0.0006223544,0.0004074372,0.001614437,0.002956348,0.002628838,0.005027954],"category_scores_gemma":[0.003068719,0.0009640832,0.00089705,0.001148676,0.0007659193,0.002419508,0.002122579,0.003232005,0.002380835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007208456,"about_ca_system_score_gemma":0.000970921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00370135,"about_ca_topic_score_gemma":0.004430233,"domain_scores_codex":[0.9995433,0.0001472936,0.00002648834,0.0001332788,0.0001070701,0.00004262712],"domain_scores_gemma":[0.999248,0.0004008061,0.00004258402,0.0001306185,0.0001378507,0.00004019569],"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":[0.000122539,0.0001204129,0.0003139926,0.0002117859,0.0001574676,0.0000863486,0.0000551539,0.6287377,0.003071748,0.02570368,0.01916205,0.3222571],"study_design_scores_gemma":[0.00000575486,0.00001158963,0.00003465291,0.00001010598,0.000006530378,0.00001043633,0.00000218601,0.9896827,0.0005829248,0.008800588,0.000847642,0.000004840162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004017056,0.001306693,0.9910508,0.000193132,0.0001363655,0.00002614473,0.0001176691,0.001817365,0.001334824],"genre_scores_gemma":[0.1540196,0.001555908,0.8266501,0.0004462305,0.0002546334,0.0002965439,0.001356323,0.001650154,0.01377041],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005027954,"threshold_uncertainty_score":0.01682019,"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."}}