{"id":"W64027530","doi":"10.1007/978-3-642-36657-4_1","title":"Deep Learning of Representations","year":2013,"lang":"en","type":"book-chapter","venue":"Intelligent systems reference library","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Initialization; Deep learning; Machine learning; Hierarchy; Representation (politics); Unsupervised learning; Feature learning; Generative grammar; Generative model; Task (project management); Engineering","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000162653,0.0003906532,0.0005796329,0.0004572115,0.0001285607,0.0004304002,0.001395682,0.0003673408,0.001979977],"category_scores_gemma":[0.00005018543,0.0003671393,0.0001898453,0.000142263,0.0001014009,0.001287208,0.0004653707,0.0007922159,0.002748743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003412542,"about_ca_system_score_gemma":0.000135331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004470899,"about_ca_topic_score_gemma":6.77342e-7,"domain_scores_codex":[0.9972232,0.0001452371,0.00102689,0.0006891458,0.0006084883,0.0003070443],"domain_scores_gemma":[0.9974557,0.0003348773,0.0009151113,0.0009332055,0.0001615607,0.0001995588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003777647,0.00001369607,0.00007993496,0.0001358684,0.00007863097,0.00001604364,0.0006329461,0.002354914,0.00002737442,0.9617248,0.002434492,0.03249756],"study_design_scores_gemma":[0.0001185816,0.0001378513,0.0001012996,0.0008895065,0.00002337563,0.00003635599,0.0003236836,0.06918539,0.0002157647,0.01557455,0.9127402,0.0006534291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001046482,0.002117628,0.2780447,0.00009261545,0.0005988225,0.0003902609,0.000004400802,0.0003507153,0.7183904],"genre_scores_gemma":[0.03939751,0.001267424,0.006534579,0.00008181247,0.000175594,0.00005046279,0.0001310923,0.00008297172,0.9522786],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9461502,"threshold_uncertainty_score":0.999878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05009056090314877,"score_gpt":0.255337457136969,"score_spread":0.2052468962338202,"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."}}