{"id":"W2155217764","doi":"10.1162/neco_a_00682","title":"Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2D and 3D Images","year":2014,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute of Mental Health; National Institute on Aging; National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Deep learning; Artificial intelligence; Convolutional neural network; Domain (mathematical analysis); Image (mathematics); Frequency domain; Deep belief network; Training (meteorology); Pattern recognition (psychology); Voxel; Machine learning; Algorithm; Computer vision; 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":[0.0006058703,0.00009596664,0.0001301388,0.0000758681,0.0001453519,0.00005737927,0.0002005168,0.00003771528,4.409369e-7],"category_scores_gemma":[0.00005303251,0.00007796897,0.00003026255,0.0002572239,0.00004499739,0.0001031713,0.00004169375,0.00006485038,7.367104e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002503219,"about_ca_system_score_gemma":0.00001207077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005549143,"about_ca_topic_score_gemma":0.00003073336,"domain_scores_codex":[0.9989644,0.0001973532,0.0002369997,0.0002661681,0.0001620818,0.0001729781],"domain_scores_gemma":[0.9992149,0.0004125355,0.0001125246,0.000127047,0.00009991148,0.00003307468],"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":[0.000009070637,0.00002073463,0.0000684113,0.000005251755,0.000002534865,1.117035e-7,0.0007218,0.9137423,0.001465664,0.01878866,0.00003345874,0.06514198],"study_design_scores_gemma":[0.0003183762,0.0001361835,0.02277795,0.000009063281,0.000004648416,0.000002366899,0.00005341903,0.9684321,0.00006177415,0.00809984,0.0000244792,0.00007978721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08872653,0.00006233593,0.9095817,0.0009843853,0.0001340836,0.0004444774,0.00000236383,0.00001907642,0.00004510478],"genre_scores_gemma":[0.8169749,9.397734e-7,0.1825908,0.0002450471,0.0001156025,0.00005441031,0.0000136402,0.000003999767,6.225815e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7282484,"threshold_uncertainty_score":0.3179482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01236193869424194,"score_gpt":0.2370243755422255,"score_spread":0.2246624368479836,"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."}}