{"id":"W2947024452","doi":"10.48550/arxiv.1906.00443","title":"Dimensionality compression and expansion in Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Curse of dimensionality; Artificial neural network; Computer science; Artificial intelligence; Generalization; Manifold (fluid mechanics); Nonlinear dimensionality reduction; Regularization (linguistics); Dimensionality reduction; Stochastic gradient descent; Deep learning; Gradient descent; Noise (video); Pattern recognition (psychology); Machine learning; Mathematics; Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001483699,0.0006480619,0.0006784701,0.0005733007,0.0003136942,0.0007732383,0.0008305206,0.0007992614,0.0006145153],"category_scores_gemma":[0.006530294,0.000433527,0.0004656348,0.0007028426,0.001549936,0.002167829,0.001596664,0.001935394,0.0001738545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175669,"about_ca_system_score_gemma":0.0005018636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00152056,"about_ca_topic_score_gemma":0.001678474,"domain_scores_codex":[0.9993293,0.0002638072,0.0000400858,0.0001246672,0.0001916615,0.00005049894],"domain_scores_gemma":[0.9983747,0.001030445,0.000160106,0.0002779753,0.0001155397,0.00004127133],"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":[0.0001246072,0.00006618533,0.001224231,0.0001310308,0.00005126751,0.00009582052,0.0002037878,0.7977023,0.005800941,0.09808443,0.002565223,0.09395018],"study_design_scores_gemma":[0.000004852189,0.00001404987,0.0001389982,0.00001039849,0.00000344313,0.00001562194,0.000007314983,0.9547935,0.001236917,0.04336426,0.0004057548,0.000004800826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07765434,0.001786021,0.9155077,0.001394516,0.00007214287,0.00004769985,0.0001709134,0.0006738135,0.002692908],"genre_scores_gemma":[0.8596165,0.001475077,0.1346768,0.0003941173,0.0001262077,0.0002000208,0.0003614305,0.0001499722,0.002999861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00152056,"threshold_uncertainty_score":0.00853014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04547687358783814,"score_gpt":0.1824946952936411,"score_spread":0.1370178217058029,"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."}}