{"id":"W2218417636","doi":"10.1609/aaai.v25i1.7925","title":"Heterogeneous Transfer Learning with RBMs","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Transfer of learning; Multi-task learning; Machine learning; Artificial intelligence; Boltzmann machine; Feature (linguistics); Task (project management); Semi-supervised learning; Feature learning; Online machine learning; Disjoint sets; Probabilistic logic; Restricted Boltzmann machine; Feature vector; Adaptation (eye); Deep 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":[],"consensus_categories":[],"category_scores_codex":[0.0003565598,0.0002127459,0.0002107774,0.0001140768,0.0002426116,0.0001752059,0.00148279,0.0000698064,0.0001861872],"category_scores_gemma":[0.0001038612,0.0001465459,0.00009586643,0.0005426912,0.0002419951,0.0003883356,0.0001363211,0.0003901128,0.0001177919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002260874,"about_ca_system_score_gemma":0.00006615242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003087472,"about_ca_topic_score_gemma":0.000008889242,"domain_scores_codex":[0.9983515,0.00002581968,0.000376486,0.0004458582,0.0004571558,0.0003432468],"domain_scores_gemma":[0.999041,0.00004659025,0.0001664724,0.000223038,0.0004178587,0.0001050632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001236093,0.0001273165,0.0005293553,0.00002133993,0.0000240737,0.000002453101,0.00875402,0.0004428078,0.01347503,0.8947133,0.000008708702,0.08177798],"study_design_scores_gemma":[0.00008598751,0.001063463,0.0006616772,0.0002599672,0.00002330089,0.00003996146,0.001799713,0.085214,0.8563522,0.0534418,0.0005380912,0.0005198933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4527327,0.00003290866,0.4404975,0.001150298,0.000415294,0.0006177976,0.000001370834,0.0003977781,0.1041544],"genre_scores_gemma":[0.9930853,0.00001656848,0.006229441,0.000183869,0.0000248131,0.00001809157,1.768608e-7,0.00001557684,0.0004262164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8428771,"threshold_uncertainty_score":0.5975969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09964339697449759,"score_gpt":0.2598105776249844,"score_spread":0.1601671806504868,"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."}}