{"id":"W2952111767","doi":"10.48550/arxiv.1206.5538","title":"Representation Learning: A Review and New Perspectives","year":2012,"lang":"en","type":"review","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Feature learning; Artificial intelligence; Representation (politics); Machine learning; Computer science; Inference; Prior probability; Nonlinear dimensionality reduction; Unsupervised learning; Deep learning; Feature (linguistics); External Data Representation; Semi-supervised learning; Bayesian probability; Dimensionality reduction","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000303337,0.0002765708,0.0007658281,0.000209945,0.0001658233,0.00009531543,0.0006017758,0.0001304374,0.0001077977],"category_scores_gemma":[0.0001227353,0.0002779698,0.0002478786,0.001185853,0.00006182716,0.0007001724,0.0003084691,0.0004534385,0.0002658024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001074726,"about_ca_system_score_gemma":0.0001675516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002485101,"about_ca_topic_score_gemma":0.000001888372,"domain_scores_codex":[0.9982624,0.0004370143,0.000215286,0.0007389761,0.00007671207,0.0002695984],"domain_scores_gemma":[0.9986278,0.0001863213,0.0003614332,0.0004960437,0.00006875516,0.0002596723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001427263,0.00002803075,0.00002773245,0.004022784,0.0001101381,0.00004244691,0.0005547701,0.00008047143,5.214438e-8,0.1557002,0.0006396804,0.8387923],"study_design_scores_gemma":[0.0001352884,0.00002617207,0.00001632512,0.002373599,0.0006581207,0.0000364169,0.0001422219,0.00105278,2.88707e-8,0.0003237037,0.9949095,0.0003258502],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[7.689235e-7,0.8755254,0.1201392,0.00005521354,0.00007588184,0.0003028747,5.025e-7,0.0001532286,0.003746916],"genre_scores_gemma":[0.0002344619,0.9862494,0.000916098,0.00006292279,0.00006881973,9.357576e-7,0.000008431431,0.00001881253,0.0124401],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9942698,"threshold_uncertainty_score":0.9999673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2470393599543467,"score_gpt":0.2658379097500409,"score_spread":0.01879854979569423,"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."}}