{"id":"W784990704","doi":"10.1007/s11063-015-9430-9","title":"Stacked Autoencoders Using Low-Power Accelerated Architectures for Object Recognition in Autonomous Systems","year":2015,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; South Dakota Agricultural Experiment Station; Canadian Institute for Advanced Research","keywords":"Computational intelligence; Computer science; Artificial intelligence; Object (grammar); Cognitive neuroscience of visual object recognition; Power (physics); Complex system; Pattern recognition (psychology); Computer vision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000208751,0.0001925077,0.0002071179,0.000156673,0.000172537,0.0004884021,0.0004429971,0.00006093268,7.234936e-7],"category_scores_gemma":[0.0000313513,0.0001749,0.00004915605,0.0005625435,0.00005362955,0.0003290183,0.00006302034,0.0002056711,0.000003581072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001190912,"about_ca_system_score_gemma":0.0001373657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006884886,"about_ca_topic_score_gemma":0.00001064818,"domain_scores_codex":[0.9984946,0.00006927025,0.0003205814,0.0004742226,0.0002049816,0.0004363911],"domain_scores_gemma":[0.9993181,0.00006405607,0.000167022,0.0002282421,0.000104907,0.0001176428],"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":[0.00006744977,0.00009605059,0.0002903546,0.0001571651,0.00001356672,0.00003413057,0.002827528,0.8961156,0.03542468,0.00007196198,0.00204704,0.06285445],"study_design_scores_gemma":[0.0005287309,0.00004059744,0.0001878426,0.00009769032,0.000005627285,0.00003442318,0.00006882081,0.9973156,0.0008163856,0.0004586682,0.0001900349,0.0002555789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7930759,0.00009356972,0.2033645,0.002301551,0.00036504,0.0005205456,0.000004075503,0.00023578,0.0000390531],"genre_scores_gemma":[0.9840069,3.973458e-7,0.01365609,0.002068986,0.0001235056,0.0001015518,0.000009698815,0.0000220261,0.00001078997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1909311,"threshold_uncertainty_score":0.7132217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08358221029294056,"score_gpt":0.2972970668946654,"score_spread":0.2137148566017248,"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."}}