{"id":"W2521893839","doi":"10.1007/s00521-016-2609-9","title":"Training echo state networks for rotation-invariant bone marrow cell classification","year":2016,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Aging; Medizinische Universität Graz; Karl-Franzens-Universität Graz; Universität Zürich; Eidgenössische Technische Hochschule Zürich","keywords":"Computer science; Invariant (physics); Pattern recognition (psychology); Segmentation; Artificial intelligence; Rotation (mathematics); Feature extraction; Context (archaeology); Bone marrow; Pathology; Mathematics; Medicine","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":[0.000342911,0.0001810776,0.0001885215,0.00007252619,0.0006732874,0.0002301143,0.0004356165,0.00006145475,0.000001066144],"category_scores_gemma":[0.00001871055,0.0001333067,0.00007416539,0.0003377603,0.00005822782,0.0002184908,0.0001769131,0.0001369845,0.000004371886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002447207,"about_ca_system_score_gemma":0.00003110541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005133719,"about_ca_topic_score_gemma":0.000002928316,"domain_scores_codex":[0.9983928,0.00006513039,0.0003797633,0.0005928625,0.00014133,0.0004281236],"domain_scores_gemma":[0.9984018,0.0006974057,0.0002374878,0.0003962343,0.0001188964,0.000148185],"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":[0.000007166123,0.00004207691,0.0003002461,0.00002686986,0.000008831743,0.000001524013,0.0002636403,0.02145113,0.007718893,0.01718969,0.0004352827,0.9525546],"study_design_scores_gemma":[0.00043889,0.00005432027,0.00122502,0.00003864497,0.000006872939,0.00001737824,0.00003229331,0.9905639,0.0002912102,0.003923846,0.003186971,0.0002207112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02563075,0.0002009665,0.9704878,0.00234027,0.0001651071,0.0006125447,0.000004649155,0.0002889224,0.0002689922],"genre_scores_gemma":[0.9674891,0.00003825888,0.0314261,0.0003298028,0.0004173709,0.00009713705,0.000007649846,0.00001831446,0.0001763059],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9691127,"threshold_uncertainty_score":0.5436088,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03426487055684507,"score_gpt":0.2656304094482516,"score_spread":0.2313655388914065,"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."}}