{"id":"W1795776692","doi":"10.1371/journal.pone.0124088","title":"Nonlinear Spike-And-Slab Sparse Coding for Interpretable Image Encoding","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Bundesministerium für Bildung und Forschung; China Scholarship Council; Deutsche Forschungsgemeinschaft; Canadian Institute for Advanced Research","keywords":"Algorithm; Pixel; Computer science; Nonlinear system; Inference; Artificial intelligence; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001227278,0.0001260779,0.0002138439,0.00006835652,0.00003739482,0.0000601793,0.00009951399,0.00005631941,0.000008767144],"category_scores_gemma":[0.000100089,0.0001329077,0.00003059331,0.00006368099,0.00002595542,0.0001581334,0.00005510936,0.0001095696,0.00001842034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003967061,"about_ca_system_score_gemma":0.000009949468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001086057,"about_ca_topic_score_gemma":0.000003460827,"domain_scores_codex":[0.9993594,0.000008813273,0.0001463798,0.0001466946,0.0001189019,0.0002197664],"domain_scores_gemma":[0.9995622,0.00005053313,0.00002372898,0.0001836083,0.00008831731,0.00009161045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003516821,0.0001669359,0.000343939,0.0001525792,0.0001758777,0.0000126153,0.0005675118,0.00009498791,0.9928945,0.0003484612,0.003879293,0.001328078],"study_design_scores_gemma":[0.0002798474,0.00007128303,0.00001076888,0.0003280198,0.0000680758,0.000003750479,0.00005780622,0.2392114,0.7580885,0.0007306038,0.0009614143,0.0001884489],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9027502,0.0006858047,0.07796335,0.0001372725,0.0001852394,0.0005363877,0.00002560219,0.001725957,0.01599017],"genre_scores_gemma":[0.8705693,0.00008404556,0.1289164,0.00005353835,0.0001673079,0.00002528857,0.000007463925,0.00004237191,0.0001342526],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2391164,"threshold_uncertainty_score":0.541982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0766875410619325,"score_gpt":0.2474714433505868,"score_spread":0.1707839022886543,"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."}}