{"id":"W2964032613","doi":"","title":"Unsupervised Learning via Meta-Learning","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Unsupervised learning; Computer science; Machine learning; Meta learning (computer science); Artificial intelligence; Cluster analysis; Embedding; Competitive learning; Feature learning; Task (project management); Conceptual clustering; Construct (python library); Semi-supervised learning; Variety (cybernetics); Multi-task learning; Fuzzy clustering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004500836,0.0001995439,0.0002433027,0.0002168116,0.0006093059,0.0001382744,0.0008402276,0.00008665841,0.0005403561],"category_scores_gemma":[0.0001049331,0.0002105558,0.0001918888,0.001102715,0.000139561,0.000809375,0.0003071284,0.0004128279,0.001167514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006009482,"about_ca_system_score_gemma":0.00005014264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004747642,"about_ca_topic_score_gemma":0.00001306496,"domain_scores_codex":[0.9983298,0.0003346226,0.0001570712,0.0006560267,0.0001189218,0.0004035339],"domain_scores_gemma":[0.9989207,0.0001490879,0.0001350249,0.000418959,0.0001819585,0.0001942702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001106755,0.000196377,0.0178876,0.00003390207,0.001241452,0.0005610335,0.005976398,0.3048681,0.004067479,0.6351985,0.0004991965,0.0293592],"study_design_scores_gemma":[0.0006203213,0.0002216634,0.001652981,0.000007349691,0.0001355431,0.00001100919,0.0003475226,0.9521658,0.0003564723,0.002857713,0.04126234,0.0003612805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07392665,0.00003970775,0.9047971,0.0001107683,0.000184445,0.00008149382,1.750381e-7,0.0005374512,0.02032217],"genre_scores_gemma":[0.9850141,0.0000193499,0.004381261,0.0002451403,0.00007896724,4.747039e-7,0.0000024144,0.00001672955,0.01024156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9110875,"threshold_uncertainty_score":0.9996102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.100827944566647,"score_gpt":0.1855868667815807,"score_spread":0.08475892221493375,"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."}}