{"id":"W870084106","doi":"10.48550/arxiv.1506.00511","title":"Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung; Nvidia","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Embedding; Deep learning; Natural language processing; Space (punctuation); Zero (linguistics); Machine learning; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009308814,0.001353478,0.0007211881,0.001441508,0.0003113995,0.0007862775,0.001413727,0.001398952,0.001085416],"category_scores_gemma":[0.0040861,0.0004088378,0.0006315253,0.0008225659,0.0005629935,0.002061257,0.000612775,0.001213375,0.0006133757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001571798,"about_ca_system_score_gemma":0.0006152085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01330248,"about_ca_topic_score_gemma":0.01847353,"domain_scores_codex":[0.9995793,0.0000933536,0.00002234929,0.0001608397,0.00006581872,0.0000783723],"domain_scores_gemma":[0.9981805,0.001004934,0.0001748595,0.0001588172,0.0003592779,0.0001215607],"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":[0.0007748621,0.000847069,0.03089915,0.000398075,0.0002001484,0.0004999404,0.0001486525,0.6255234,0.01037287,0.004334382,0.01979516,0.3062063],"study_design_scores_gemma":[0.000005850548,0.00002441996,0.0009066071,0.000009264256,0.00000711944,0.00001711862,0.00001225966,0.9958752,0.001436958,0.001542342,0.0001581798,0.00000466578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7891915,0.002668959,0.1960147,0.000850675,0.0002999865,0.0001381819,0.003260339,0.00395861,0.003616945],"genre_scores_gemma":[0.9692561,0.000284809,0.02243537,0.0001425552,0.00005561204,0.00004832441,0.004787757,0.00004911144,0.002940394],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01330248,"threshold_uncertainty_score":0.0264501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1694283030760944,"score_gpt":0.2197351088161322,"score_spread":0.05030680574003782,"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."}}