{"id":"W2410946393","doi":"10.1109/acpr.2015.7486451","title":"IAPR keynote lecture IV: Deep learning","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Deep neural networks; Transfer of learning; Variety (cybernetics); Language understanding; Artificial neural network; Recurrent neural network; Competence (human resources); Cognitive science; Machine learning; Data science; Psychology","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":[0.0002052232,0.00006929818,0.00008046815,0.00006035456,0.00005911326,0.0001298685,0.0003257981,0.0000472124,0.0002310852],"category_scores_gemma":[0.0001849894,0.00005784295,0.00004107659,0.0002023462,0.00001284618,0.0002103286,0.00008527205,0.0001100564,0.001255453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002118395,"about_ca_system_score_gemma":0.00002891741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572061,"about_ca_topic_score_gemma":0.00001792166,"domain_scores_codex":[0.9993051,0.00005616835,0.00008718792,0.000191168,0.0001960571,0.0001643339],"domain_scores_gemma":[0.9995121,0.00005221842,0.00002595941,0.0001935561,0.00007659196,0.0001395129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002814806,0.00001801026,0.0004534225,0.000001496815,0.00000751725,0.0000118281,0.0004561962,0.00007840736,0.0002169824,0.004233055,0.001813259,0.992707],"study_design_scores_gemma":[0.001052908,0.0002227454,0.003337361,0.00001969306,0.00001200296,0.0001721603,0.000340296,0.5989019,0.03868158,0.02647589,0.3300638,0.0007196338],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005418416,0.00006356379,0.8654551,0.00127643,0.0002149864,0.00003856067,6.916289e-8,0.0003587691,0.1271741],"genre_scores_gemma":[0.6631036,0.000009593974,0.3296945,0.001437804,0.0001088022,0.000005674905,0.000001213774,0.000008904231,0.005629933],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9919873,"threshold_uncertainty_score":0.9995222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03173245847646136,"score_gpt":0.2436212647191048,"score_spread":0.2118888062426434,"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."}}