{"id":"W2963559171","doi":"","title":"Learning Convolutional Neural Networks using Hybrid Orthogonal Projection and Estimation","year":2016,"lang":"en","type":"article","venue":"Asian Conference on Machine Learning","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Convolutional neural network; Orthogonality; Computer science; Pooling; Pattern recognition (psychology); Block (permutation group theory); Artificial intelligence; Feature (linguistics); Convolution (computer science); Projection (relational algebra); Dimension (graph theory); Feature extraction; Kernel (algebra); Algorithm; Artificial neural network; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001513167,0.0001651358,0.0001255794,0.00009925014,0.0003034196,0.00009492267,0.00007139797,0.00005761378,0.00006020002],"category_scores_gemma":[0.00005933498,0.0001383126,0.00002805277,0.00010951,0.00006333677,0.0002286073,0.0000299453,0.0004240293,0.000007595541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005538169,"about_ca_system_score_gemma":0.00002102735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001173604,"about_ca_topic_score_gemma":0.000002692256,"domain_scores_codex":[0.9991977,0.00005236561,0.0001765114,0.000224292,0.0001208469,0.0002282569],"domain_scores_gemma":[0.9996881,0.00004422287,0.00006927369,0.00008239265,0.00005698672,0.00005904762],"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":[0.00001785758,0.00001408923,0.00696482,0.0000337967,0.00001677739,0.00000400726,0.00008727713,0.1354909,0.006835039,0.004568238,0.00003082881,0.8459364],"study_design_scores_gemma":[0.0001873845,0.00006431725,0.001669449,0.00009610932,0.00001068769,0.00005434265,0.0000190769,0.9964926,0.0002893127,0.0005841624,0.0003480342,0.0001845456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1224727,0.00007345542,0.8742508,0.0004153535,0.00006101899,0.0001430063,0.000003945629,0.000763389,0.001816297],"genre_scores_gemma":[0.9924877,0.0000414895,0.007135593,0.00001993641,0.00007966178,0.00002439848,0.00003021819,0.00003270132,0.000148311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.870015,"threshold_uncertainty_score":0.5640225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01695609749781053,"score_gpt":0.2573449794490105,"score_spread":0.2403888819512,"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."}}