{"id":"W2280728065","doi":"","title":"Stage-wise Training: An Improved Feature Learning Strategy for Deep Models","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Regularization (linguistics); Curse of dimensionality; Machine learning; Artificial neural network; Decoupling (probability); Deep learning; Feature (linguistics); Context (archaeology); Process (computing); Generalization; Feature extraction; Feature learning; Mathematics; Engineering","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001253246,0.0001994387,0.0002448925,0.0001312847,0.0003229286,0.002318503,0.0005452071,0.0001350145,4.464794e-7],"category_scores_gemma":[0.0001385467,0.0001718796,0.00005249082,0.0003278614,0.00002588579,0.01343373,0.00004925594,0.0002604883,0.000004982932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006352022,"about_ca_system_score_gemma":0.0002810597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003160341,"about_ca_topic_score_gemma":0.000001814961,"domain_scores_codex":[0.9984204,0.0001665143,0.0004559366,0.0002235455,0.0003591689,0.0003744256],"domain_scores_gemma":[0.9983848,0.00005123944,0.0003917766,0.0002521827,0.0007064673,0.0002135896],"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":[0.00007249558,0.00001787956,0.000009167332,0.0003708185,0.000009027263,0.000002647138,0.02701516,0.5262349,0.000574397,0.003687639,0.0003279112,0.4416779],"study_design_scores_gemma":[0.0008862584,0.0002843128,0.000006622444,0.00003950754,0.000005752661,0.00004449208,0.002971405,0.9905187,0.0002691722,0.000626214,0.004123279,0.0002243218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003540706,0.0002357779,0.9923657,0.0001239429,0.0005215576,0.0004161638,0.000004341927,0.0004315983,0.002360237],"genre_scores_gemma":[0.9550009,9.725094e-7,0.04319633,0.000268415,0.0001725945,0.00007367236,0.00005575861,0.00001559165,0.001215771],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9514602,"threshold_uncertainty_score":0.9987172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1193691106511897,"score_gpt":0.3293162928280917,"score_spread":0.2099471821769019,"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."}}