{"id":"W3184033781","doi":"10.3390/s21144805","title":"OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection","year":2021,"lang":"en","type":"article","venue":"MDPI (MDPI AG)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Deep learning; Computer science; Anomaly detection; Latency (audio); Software deployment; Field-programmable gate array; Artificial intelligence; Field (mathematics); Embedded system; Computer architecture; Real-time computing; Telecommunications; Operating system","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":[0.0002360266,0.0002835448,0.0002916231,0.0001546386,0.0005404941,0.0002643865,0.0006504664,0.0001520707,0.00004457301],"category_scores_gemma":[0.00005951021,0.0002710825,0.0002191361,0.000779835,0.00005718953,0.000101918,0.0001325902,0.000292039,0.00009410574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216486,"about_ca_system_score_gemma":0.00009799461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000474351,"about_ca_topic_score_gemma":0.000241139,"domain_scores_codex":[0.9979786,0.00008927819,0.0003744972,0.000747747,0.0002799761,0.0005299078],"domain_scores_gemma":[0.9982413,0.0002999536,0.0001784552,0.0009136964,0.000198178,0.0001684089],"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":[0.0001742199,0.0009417444,0.001084256,0.0002236786,0.0003595152,0.0000810634,0.001265809,0.5444736,0.01886164,0.06280105,0.02141535,0.348318],"study_design_scores_gemma":[0.0007910376,0.0006975551,0.009143996,0.0000740552,0.00008113115,0.0001316503,0.00005143784,0.7763501,0.04123929,0.03413886,0.1363813,0.0009195571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01766901,0.0002181274,0.9762555,0.00126487,0.0003991062,0.0005195786,0.00001271102,0.0009051683,0.002755887],"genre_scores_gemma":[0.9385828,0.00001225105,0.05789063,0.001446382,0.0004926394,0.0002103957,0.00001158777,0.00003640069,0.001316957],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9209138,"threshold_uncertainty_score":0.9999741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01512265854475249,"score_gpt":0.2600207983048395,"score_spread":0.2448981397600871,"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."}}