{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004838104,0.0003586198,0.0003262433,0.0003089245,0.0004878718,0.0003048491,0.001401748,0.0003426629,0.00003424265],"category_scores_gemma":[0.00008981433,0.0004495251,0.0002153011,0.0006806756,0.0001946854,0.0007242651,0.00177702,0.001085636,0.0000363626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004849531,"about_ca_system_score_gemma":0.0003656391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001482411,"about_ca_topic_score_gemma":0.00004032749,"domain_scores_codex":[0.9975738,0.0003034244,0.0003137522,0.001054812,0.0002031706,0.0005510297],"domain_scores_gemma":[0.9979663,0.0001360379,0.000373151,0.0007623734,0.000394615,0.0003675026],"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":[0.00001620403,0.00004173948,0.004703068,0.00001088707,0.00005470115,0.0001018818,0.0002587002,0.9303417,0.00001762071,0.06391422,0.0001644588,0.0003748614],"study_design_scores_gemma":[0.0004944985,0.00003255602,0.0010205,0.00005060833,0.00006119737,0.00002485584,0.0002962406,0.9908856,0.00000155214,0.006405789,0.0002990865,0.0004275193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.135173,0.0001363868,0.8596761,0.00003859885,0.001154544,0.0002105977,0.000008675265,0.0003769693,0.003225053],"genre_scores_gemma":[0.9912217,0.00002001169,0.007643479,0.0001923369,0.000229465,9.663916e-7,0.00005023263,0.00002491895,0.0006168957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8560486,"threshold_uncertainty_score":0.9997957,"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."}}