{"id":"W173210115","doi":"10.1007/978-3-642-38847-7_20","title":"Robust Hierarchical and Sparse Representation of Natural Sounds in High-Dimensional Space","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Curse of dimensionality; Speech recognition; Pattern recognition (psychology); Sparse approximation; Feature vector; Neural coding; Noise (video); Signal processing; Digital signal processing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006898507,0.0003235082,0.0004753323,0.0009947538,0.00008140824,0.0002676515,0.001194952,0.0002664406,0.00001514711],"category_scores_gemma":[0.0001118073,0.0002949863,0.00006319597,0.0006152513,0.0007478604,0.0007620638,0.001033888,0.0008616725,0.00000782762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001205817,"about_ca_system_score_gemma":0.0002835616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001514027,"about_ca_topic_score_gemma":0.0001434521,"domain_scores_codex":[0.9971303,0.00008142478,0.0005138416,0.001092196,0.0008361014,0.0003461661],"domain_scores_gemma":[0.9980761,0.0005377554,0.0002814875,0.0007896301,0.0002143753,0.0001006392],"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":[0.00003087453,0.0001092738,0.0007523124,0.0000740024,0.0000192635,0.00008807711,0.003199656,0.1123856,0.001809448,0.4304275,0.0001862453,0.4509178],"study_design_scores_gemma":[0.0003369157,0.0001440488,0.002857761,0.0002662738,0.000003391778,0.0000589575,2.245481e-7,0.6918023,0.003734201,0.300292,0.00007882952,0.0004251226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007457211,0.0002114871,0.9888777,0.001765308,0.0004814673,0.0003848797,0.000001883064,0.00009597868,0.0007241245],"genre_scores_gemma":[0.4981492,0.0000192228,0.5009891,0.00052556,0.00007371099,0.000006868141,0.000005122684,0.00001327376,0.0002178798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5794167,"threshold_uncertainty_score":0.9999502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02286788164746955,"score_gpt":0.2572222860201066,"score_spread":0.234354404372637,"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."}}