{"id":"W2613903212","doi":"10.1109/globalsip.2017.8309150","title":"A feature embedding strategy for high-level CNN representations from multiple convnets","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Computer science; Embedding; Normalization (sociology); Convolutional neural network; Feature extraction; Principal component analysis; Feature (linguistics); Feature vector; Exploit; Contextual image classification; Image (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":[0.00005118418,0.0001241864,0.0001335066,0.00002830935,0.0008361183,0.0004054655,0.001269016,0.0000639567,0.00001641127],"category_scores_gemma":[0.0001317606,0.0001136737,0.00005324578,0.0000730083,0.00005481748,0.0008227507,0.0002777222,0.0001073159,0.00004153201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002068833,"about_ca_system_score_gemma":0.00003140567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00018812,"about_ca_topic_score_gemma":0.0002661654,"domain_scores_codex":[0.9989743,0.00001450065,0.0001303751,0.0005094787,0.0001255705,0.0002457407],"domain_scores_gemma":[0.9977474,0.0004376247,0.0001731426,0.001445553,0.0001028342,0.00009346545],"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":[0.00002815228,0.0001329659,0.002955249,0.0000110702,0.00008465456,0.00001192496,0.000348463,0.01984108,0.02085111,0.7700732,0.08598038,0.09968175],"study_design_scores_gemma":[0.001567934,0.00005331741,0.0535888,0.00001915261,0.00001719809,0.000004970887,0.00006681114,0.7564574,0.0201338,0.1562572,0.01138023,0.0004531363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007111182,0.00002678241,0.9837156,0.006807782,0.0002378449,0.0004993181,0.00007663067,0.0002022288,0.001322641],"genre_scores_gemma":[0.6078104,0.000005085963,0.3887537,0.0001717752,0.0001302973,0.0001482499,0.0000317567,0.000008341479,0.002940342],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7366163,"threshold_uncertainty_score":0.6430831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09048114161378658,"score_gpt":0.3638573489804966,"score_spread":0.27337620736671,"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."}}